meta-llama-llama-3-1-8b

developer_uid: Jellywibble

submission_id: meta-llama-llama-3-1-8b_v1

model_name: meta-llama-llama-3-1-8b_v1

model_group: meta-llama/Llama-3.1-8B

status: inactive

timestamp: 2024-12-23T00:12:59+00:00

num_battles: 32399

num_wins: 13467

celo_rating: 1195.28

family_friendly_score: 0.5962000000000001

family_friendly_standard_error: 0.006938956117457438

submission_type: basic

model_repo: meta-llama/Llama-3.1-8B

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8653471464280253, 'latency_mean': 1.1555103719234467, 'latency_p50': 1.1627949476242065, 'latency_p90': 1.2700793504714967}, {'batch_size': 4, 'throughput': 1.8485815444679794, 'latency_mean': 2.1556961584091185, 'latency_p50': 2.149769425392151, 'latency_p90': 2.3889614582061767}, {'batch_size': 5, 'throughput': 1.981186731468096, 'latency_mean': 2.5096730411052706, 'latency_p50': 2.5146907567977905, 'latency_p90': 2.768066573143005}, {'batch_size': 8, 'throughput': 2.210917239360481, 'latency_mean': 3.6006868517398836, 'latency_p50': 3.639891743659973, 'latency_p90': 4.048470473289489}, {'batch_size': 10, 'throughput': 2.255491507310632, 'latency_mean': 4.393661457300186, 'latency_p50': 4.383094787597656, 'latency_p90': 4.97364113330841}, {'batch_size': 12, 'throughput': 2.3006755385910553, 'latency_mean': 5.17232612490654, 'latency_p50': 5.166746258735657, 'latency_p90': 5.8558865785598755}, {'batch_size': 15, 'throughput': 2.3193414748686836, 'latency_mean': 6.383356140851975, 'latency_p50': 6.360876083374023, 'latency_p90': 7.230839204788208}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: meta-llama-llama-3-1-8b_v1

is_internal_developer: True

language_model: meta-llama/Llama-3.1-8B

model_size: 8B

ranking_group: single

throughput_3p7s: 2.23

us_pacific_date: 2024-12-22

win_ratio: 0.41566097719065404

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}

formatter: {'memory_template': '### Instruction:\n{memory}\n', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:', 'truncate_by_message': False}

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-llama-3-1-8b-v1-mkmlizer
Waiting for job on meta-llama-llama-3-1-8b-v1-mkmlizer to finish
meta-llama-llama-3-1-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meta-llama-llama-3-1-8b-v1-mkmlizer: ║     _____            __           __                                ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║       /___/                                                         ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║                                                                     ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║  https://mk1.ai                                                     ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║                                                                     ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║  belonging to:                                                      ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║                                                                     ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ║                                                                     ║
meta-llama-llama-3-1-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meta-llama-llama-3-1-8b-v1-mkmlizer: Downloaded to shared memory in 43.799s
meta-llama-llama-3-1-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp38anw1d6, device:0
meta-llama-llama-3-1-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meta-llama-llama-3-1-8b-v1-mkmlizer: quantized model in 26.203s
meta-llama-llama-3-1-8b-v1-mkmlizer: Processed model meta-llama/Llama-3.1-8B in 70.002s
meta-llama-llama-3-1-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
meta-llama-llama-3-1-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meta-llama-llama-3-1-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-v1
meta-llama-llama-3-1-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-v1/config.json
meta-llama-llama-3-1-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-v1/special_tokens_map.json
meta-llama-llama-3-1-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-v1/tokenizer_config.json
meta-llama-llama-3-1-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-v1/tokenizer.json
meta-llama-llama-3-1-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-v1/flywheel_model.0.safetensors
meta-llama-llama-3-1-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 31.76it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:06, 45.24it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 49.13it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 50.29it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:04, 57.25it/s]
Loading 0:  16%|█▌        | 46/291 [00:00<00:04, 51.89it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:04, 53.01it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:04, 54.78it/s]
Loading 0:  22%|██▏       | 64/291 [00:01<00:04, 51.48it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:04, 52.30it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 53.60it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:04, 50.41it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:06, 32.53it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:05, 37.65it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 38.99it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 40.41it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 47.07it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 46.70it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 47.19it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 50.32it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 49.00it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 50.80it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 53.14it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:02, 50.14it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 51.31it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 53.60it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 50.88it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 53.33it/s]
Loading 0:  64%|██████▍   | 186/291 [00:03<00:02, 51.26it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:02, 34.33it/s]
Loading 0:  68%|██████▊   | 198/291 [00:04<00:02, 38.84it/s]
Loading 0:  70%|██████▉   | 203/291 [00:04<00:02, 36.39it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 44.78it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 44.57it/s]
Loading 0:  76%|███████▋  | 222/291 [00:04<00:01, 44.00it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 49.67it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 48.10it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 48.84it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 50.60it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 48.26it/s]
Loading 0:  89%|████████▊ | 258/291 [00:05<00:00, 47.09it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 50.46it/s]
Loading 0:  93%|█████████▎| 271/291 [00:05<00:00, 47.97it/s]
Loading 0:  95%|█████████▍| 276/291 [00:05<00:00, 46.22it/s]
Loading 0:  97%|█████████▋| 281/291 [00:05<00:00, 46.17it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 42.38it/s]
Loading 0: 100%|██████████| 291/291 [00:11<00:00,  3.06it/s]
                                                            
Job meta-llama-llama-3-1-8b-v1-mkmlizer completed after 94.59s with status: succeeded
Stopping job with name meta-llama-llama-3-1-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.18s
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 meta-llama-llama-3-1-8b-v1
Waiting for inference service meta-llama-llama-3-1-8b-v1 to be ready
Inference service meta-llama-llama-3-1-8b-v1 ready after 281.48395562171936s
Pipeline stage MKMLDeployer completed in 282.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.556312084197998s
Received healthy response to inference request in 1.063459873199463s
Received healthy response to inference request in 1.1793856620788574s
Received healthy response to inference request in 1.5060827732086182s
Received healthy response to inference request in 0.7157602310180664s
5 requests
0 failed requests
5th percentile: 0.7853001594543457
10th percentile: 0.854840087890625
20th percentile: 0.9939199447631836
30th percentile: 1.0866450309753417
40th percentile: 1.1330153465270996
50th percentile: 1.1793856620788574
60th percentile: 1.3100645065307617
70th percentile: 1.440743350982666
80th percentile: 1.5161286354064942
90th percentile: 1.5362203598022461
95th percentile: 1.546266222000122
99th percentile: 1.5543029117584228
mean time: 1.2042001247406007
Pipeline stage StressChecker completed in 7.34s
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 0.67s
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 0.61s
Shutdown handler de-registered
meta-llama-llama-3-1-8b_v1 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 meta-llama-llama-3-1-8b-v1-profiler
Waiting for inference service meta-llama-llama-3-1-8b-v1-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 2219.50s
Shutdown handler de-registered
meta-llama-llama-3-1-8b_v1 status is now inactive due to auto deactivation removed underperforming models