submission_id: nousresearch-meta-llama_4939_v30
developer_uid: end_to_end_test
best_of: 4
celo_rating: 1185.01
display_name: nousresearch-meta-llama_4939_v30
family_friendly_score: 0.0
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': 0.99, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
ineligible_reason: model is only for e2e test
is_internal_developer: True
language_model: NousResearch/Meta-Llama-3.1-8B-Instruct
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: NousResearch/Meta-Llama-
model_name: nousresearch-meta-llama_4939_v30
model_num_parameters: 8030261248.0
model_repo: NousResearch/Meta-Llama-3.1-8B-Instruct
model_size: 8B
num_battles: 6061
num_wins: 2636
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-08-30T04:41:51+00:00
us_pacific_date: 2024-08-29
win_ratio: 0.43491173073750206
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4939-v30-mkmlizer
Waiting for job on nousresearch-meta-llama-4939-v30-mkmlizer to finish
nousresearch-meta-llama-4939-v30-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4939-v30-mkmlizer: ║     _____            __           __                                ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║       /___/                                                         ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║  Version: 0.10.1                                                    ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║  https://mk1.ai                                                     ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║  The license key for the current software has been verified as      ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║  belonging to:                                                      ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║  Chai Research Corp.                                                ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
nousresearch-meta-llama-4939-v30-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v30-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4939-v30-mkmlizer: Downloaded to shared memory in 32.334s
nousresearch-meta-llama-4939-v30-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk_q31pxq, device:0
nousresearch-meta-llama-4939-v30-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4939-v30-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4939-v30-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4939-v30-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v30
nousresearch-meta-llama-4939-v30-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v30/special_tokens_map.json
nousresearch-meta-llama-4939-v30-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v30/config.json
nousresearch-meta-llama-4939-v30-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v30/tokenizer_config.json
nousresearch-meta-llama-4939-v30-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v30/tokenizer.json
nousresearch-meta-llama-4939-v30-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v30/flywheel_model.0.safetensors
nousresearch-meta-llama-4939-v30-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 35.74it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 49.51it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:04, 58.70it/s]
Loading 0:  10%|▉         | 29/291 [00:00<00:04, 56.35it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:04, 57.10it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:05, 49.76it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 51.99it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 53.92it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 54.63it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 58.13it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:03, 52.59it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:05, 37.59it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:04, 41.66it/s]
Loading 0:  34%|███▍      | 99/291 [00:02<00:04, 43.09it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:04, 39.02it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 47.08it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 44.15it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:04, 41.41it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 46.92it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 46.94it/s]
Loading 0:  48%|████▊     | 141/291 [00:02<00:03, 46.88it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 52.70it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:02, 50.53it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 50.53it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 51.57it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 44.51it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 49.43it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:02, 51.16it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 34.24it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 35.07it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 39.74it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:02, 39.67it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 39.28it/s]
Loading 0:  75%|███████▌  | 219/291 [00:04<00:01, 43.77it/s]
Loading 0:  77%|███████▋  | 224/291 [00:04<00:01, 44.67it/s]
Loading 0:  79%|███████▉  | 230/291 [00:05<00:01, 42.47it/s]
Loading 0:  81%|████████▏ | 237/291 [00:05<00:01, 48.05it/s]
Loading 0:  84%|████████▎ | 243/291 [00:05<00:00, 48.08it/s]
Loading 0:  85%|████████▌ | 248/291 [00:05<00:01, 42.43it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 50.64it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 47.42it/s]
Loading 0:  92%|█████████▏| 267/291 [00:05<00:00, 43.82it/s]
Loading 0:  94%|█████████▍| 273/291 [00:05<00:00, 46.79it/s]
Loading 0:  96%|█████████▌| 278/291 [00:06<00:00, 47.26it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 42.94it/s]
Loading 0:  99%|█████████▉| 288/291 [00:11<00:00,  3.11it/s]
                                                            

Job nousresearch-meta-llama-4939-v30-mkmlizer completed after 76.81s with status: succeeded
Stopping job with name nousresearch-meta-llama-4939-v30-mkmlizer
Pipeline stage MKMLizer completed in 77.95s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.28s
Running pipeline stage MKMLDeployer
Creating inference service nousresearch-meta-llama-4939-v30
Waiting for inference service nousresearch-meta-llama-4939-v30 to be ready
Inference service nousresearch-meta-llama-4939-v30 ready after 171.98269987106323s
Pipeline stage MKMLDeployer completed in 172.85s
Running pipeline stage StressChecker
Received healthy response to inference request in 8.786092042922974s
Received healthy response to inference request in 1.6722309589385986s
Received healthy response to inference request in 1.6955149173736572s
Received healthy response to inference request in 1.2773170471191406s
Received healthy response to inference request in 1.478391170501709s
5 requests
0 failed requests
5th percentile: 1.3175318717956543
10th percentile: 1.357746696472168
20th percentile: 1.4381763458251953
30th percentile: 1.5171591281890868
40th percentile: 1.5946950435638427
50th percentile: 1.6722309589385986
60th percentile: 1.681544542312622
70th percentile: 1.6908581256866455
80th percentile: 3.1136303424835217
90th percentile: 5.949861192703247
95th percentile: 7.36797661781311
99th percentile: 8.502468957901002
mean time: 2.981909227371216
Pipeline stage StressChecker completed in 17.13s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
triggered trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 3.03s
nousresearch-meta-llama_4939_v30 status is now deployed due to DeploymentManager action
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.50s
Running pipeline stage MKMLProfilerDeployer
Creating inference service nousresearch-meta-llama-4939-v30-profiler
Waiting for inference service nousresearch-meta-llama-4939-v30-profiler to be ready
Inference service nousresearch-meta-llama-4939-v30-profiler ready after 183.44672322273254s
Pipeline stage MKMLProfilerDeployer completed in 184.55s
Running pipeline stage MKMLProfilerDeleter
Checking if service nousresearch-meta-llama-4939-v30-profiler is running
Tearing down inference service nousresearch-meta-llama-4939-v30-profiler
Service nousresearch-meta-llama-4939-v30-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.25s
nousresearch-meta-llama_4939_v30 status is now inactive due to admin request
nousresearch-meta-llama_4939_v30 status is now torndown due to DeploymentManager action
Starting job with name nousresearch-meta-llama-4939-v31-mkmlizer
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.43s
Running pipeline stage MKMLProfilerDeployer
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLProfilerDeployer completed in 0.20s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.44s
Running pipeline stage MKMLProfilerDeployer
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLProfilerDeployer completed in 0.22s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.44s
Running pipeline stage MKMLProfilerDeployer
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLProfilerDeployer completed in 0.20s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.60s
Running pipeline stage MKMLProfilerDeployer
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLProfilerDeployer completed in 0.26s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.62s
Running pipeline stage MKMLProfilerDeployer
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLProfilerDeployer completed in 0.29s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.49s
Running pipeline stage MKMLProfilerDeployer
Creating inference service nousresearch-meta-llama-4939-v30-profiler
Waiting for inference service nousresearch-meta-llama-4939-v30-profiler to be ready
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.60s
Running pipeline stage MKMLProfilerDeployer
Creating inference service nousresearch-meta-llama-4939-v30-profiler
Ignoring service nousresearch-meta-llama-4939-v30-profiler already deployed
Waiting for inference service nousresearch-meta-llama-4939-v30-profiler to be ready
Tearing down inference service nousresearch-meta-llama-4939-v30-profiler
%s, retrying in %s seconds...
Creating inference service nousresearch-meta-llama-4939-v30-profiler
Waiting for inference service nousresearch-meta-llama-4939-v30-profiler to be ready