submission_id: meta-llama-meta-llama-3-8b_v14
developer_uid: chai_backend_admin
best_of: 8
celo_rating: 1199.32
display_name: meta-llama-meta-llama-3-8b_v14
family_friendly_score: 0.5388524590163934
family_friendly_standard_error: 0.006356754789909056
formatter: {'memory_template': '### Instruction:\n{memory}\n', 'prompt_template': '### Input:\n{prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', 'You:', '\n', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
is_internal_developer: True
language_model: meta-llama/Meta-Llama-3-8B
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: meta-llama/Meta-Llama-3-
model_name: meta-llama-meta-llama-3-8b_v14
model_num_parameters: 8030261248.0
model_repo: meta-llama/Meta-Llama-3-8B
model_size: 8B
num_battles: 6377
num_wins: 2678
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-10-10T21:41:15+00:00
us_pacific_date: 2024-10-10
win_ratio: 0.4199466833934452
Download Preference Data
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 meta-llama-meta-llama-3-8b-v14-mkmlizer
Waiting for job on meta-llama-meta-llama-3-8b-v14-mkmlizer to finish
meta-llama-meta-llama-3-8b-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ _____ __ __ ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ /___/ ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ Version: 0.11.12 ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ https://mk1.ai ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ The license key for the current software has been verified as ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ belonging to: ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ Chai Research Corp. ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ║ ║
meta-llama-meta-llama-3-8b-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission sao10k-mn-12b-lyra-v4a1_v3: ('http://chaiml-llama-8b-pairwis-8189-v27-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:55342->127.0.0.1:8080: read: connection reset by peer\n')
meta-llama-meta-llama-3-8b-v14-mkmlizer: Downloaded to shared memory in 34.926s
meta-llama-meta-llama-3-8b-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_5vtdwr1, device:0
meta-llama-meta-llama-3-8b-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meta-llama-meta-llama-3-8b-v14-mkmlizer: quantized model in 26.420s
meta-llama-meta-llama-3-8b-v14-mkmlizer: Processed model meta-llama/Meta-Llama-3-8B in 61.346s
meta-llama-meta-llama-3-8b-v14-mkmlizer: creating bucket guanaco-mkml-models
meta-llama-meta-llama-3-8b-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meta-llama-meta-llama-3-8b-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v14
meta-llama-meta-llama-3-8b-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v14/config.json
meta-llama-meta-llama-3-8b-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v14/special_tokens_map.json
meta-llama-meta-llama-3-8b-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v14/tokenizer_config.json
meta-llama-meta-llama-3-8b-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v14/tokenizer.json
meta-llama-meta-llama-3-8b-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v14/flywheel_model.0.safetensors
meta-llama-meta-llama-3-8b-v14-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:08, 32.36it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:06, 45.28it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:05, 49.27it/s] Loading 0: 11%|█ | 32/291 [00:00<00:05, 51.09it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:04, 58.37it/s] Loading 0: 16%|█▌ | 47/291 [00:00<00:04, 56.93it/s] Loading 0: 18%|█▊ | 53/291 [00:00<00:04, 55.86it/s] Loading 0: 20%|██ | 59/291 [00:01<00:04, 48.32it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 55.86it/s] Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 52.72it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:03, 53.21it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:05, 36.15it/s] Loading 0: 31%|███ | 90/291 [00:01<00:05, 38.82it/s] Loading 0: 33%|███▎ | 95/291 [00:02<00:05, 35.65it/s] Loading 0: 35%|███▌ | 102/291 [00:02<00:04, 41.65it/s] Loading 0: 37%|███▋ | 107/291 [00:02<00:04, 42.10it/s] Loading 0: 39%|███▉ | 113/291 [00:02<00:04, 39.15it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 46.91it/s] Loading 0: 44%|████▎ | 127/291 [00:02<00:03, 45.01it/s] Loading 0: 45%|████▌ | 132/291 [00:02<00:03, 45.25it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 50.99it/s] Loading 0: 50%|████▉ | 145/291 [00:03<00:02, 48.85it/s] Loading 0: 52%|█████▏ | 151/291 [00:03<00:02, 49.58it/s] Loading 0: 54%|█████▍ | 158/291 [00:03<00:02, 47.07it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 54.37it/s] Loading 0: 59%|█████▉ | 172/291 [00:03<00:02, 51.49it/s] Loading 0: 62%|██████▏ | 179/291 [00:03<00:02, 53.40it/s] Loading 0: 64%|██████▎ | 185/291 [00:03<00:01, 53.48it/s] Loading 0: 66%|██████▌ | 191/291 [00:04<00:02, 34.01it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 35.43it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 40.30it/s] Loading 0: 71%|███████▏ | 208/291 [00:04<00:02, 41.11it/s] Loading 0: 73%|███████▎ | 213/291 [00:04<00:01, 42.28it/s] Loading 0: 75%|███████▌ | 219/291 [00:04<00:01, 46.20it/s] Loading 0: 77%|███████▋ | 224/291 [00:04<00:01, 45.98it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 46.51it/s] Loading 0: 81%|████████ | 235/291 [00:05<00:01, 46.05it/s] Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 45.50it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 50.03it/s] Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 46.76it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 46.24it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 50.65it/s] Loading 0: 93%|█████████▎| 271/291 [00:05<00:00, 48.21it/s] Loading 0: 95%|█████████▍| 276/291 [00:05<00:00, 47.48it/s] Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 43.74it/s] Loading 0: 99%|█████████▊| 287/291 [00:11<00:01, 3.23it/s]
Job meta-llama-meta-llama-3-8b-v14-mkmlizer completed after 84.31s with status: succeeded
Stopping job with name meta-llama-meta-llama-3-8b-v14-mkmlizer
Pipeline stage MKMLizer completed in 84.85s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service meta-llama-meta-llama-3-8b-v14
Waiting for inference service meta-llama-meta-llama-3-8b-v14 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
Inference service meta-llama-meta-llama-3-8b-v14 ready after 140.5411446094513s
Pipeline stage MKMLDeployer completed in 141.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1370129585266113s
Received healthy response to inference request in 1.3349363803863525s
Received healthy response to inference request in 1.186072826385498s
Received healthy response to inference request in 1.2554728984832764s
Received healthy response to inference request in 1.2886412143707275s
5 requests
0 failed requests
5th percentile: 1.1999528408050537
10th percentile: 1.2138328552246094
20th percentile: 1.2415928840637207
30th percentile: 1.2621065616607665
40th percentile: 1.275373888015747
50th percentile: 1.2886412143707275
60th percentile: 1.3071592807769776
70th percentile: 1.3256773471832275
80th percentile: 1.4953516960144044
90th percentile: 1.816182327270508
95th percentile: 1.9765976428985594
99th percentile: 2.1049298954010007
mean time: 1.4404272556304931
Pipeline stage StressChecker completed in 8.48s
Shutdown handler de-registered
meta-llama-meta-llama-3-8b_v14 status is now deployed due to DeploymentManager action
meta-llama-meta-llama-3-8b_v14 status is now inactive due to auto deactivation removed underperforming models
meta-llama-meta-llama-3-8b_v14 status is now torndown due to DeploymentManager action