submission_id: nousresearch-meta-llama_4941_v64
developer_uid: end_to_end_test
best_of: 4
display_name: nousresearch-meta-llama_4941_v64
family_friendly_score: 0.0
formatter: {'memory_template': 'character: {bot_name} {memory}\n', 'prompt_template': '{prompt}', 'bot_template': '{bot_name}: {message}', 'user_template': '{user_name}: {message}', '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-3-8B-Instruct
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: NousResearch/Meta-Llama-
model_name: nousresearch-meta-llama_4941_v64
model_num_parameters: 8030261248.0
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
model_size: 8B
num_battles: 22
num_wins: 6
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}', 'memory_template': 'character: {bot_name} {memory}\n', 'prompt_template': '{prompt}', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}'}
reward_repo: ChaiML/reward_models_100_170000000_cp_498032
status: torndown
submission_type: basic
timestamp: 2024-07-01T18:48:48+00:00
us_pacific_date: 2024-07-01
win_ratio: 0.2727272727272727
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v64-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v64-mkmlizer to finish
nousresearch-meta-llama-4941-v64-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v64-mkmlizer: ║     _____            __           __                                ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║       /___/                                                         ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║  Version: 0.8.14                                                    ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║  https://mk1.ai                                                     ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║  The license key for the current software has been verified as      ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║  belonging to:                                                      ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║  Chai Research Corp.                                                ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
nousresearch-meta-llama-4941-v64-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v64-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v64-mkmlizer: Downloaded to shared memory in 20.373s
nousresearch-meta-llama-4941-v64-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v64-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v64-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:09, 29.88it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:03, 81.23it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:02, 100.60it/s]
Loading 0:  15%|█▌        | 45/291 [00:00<00:02, 114.11it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 116.35it/s]
Loading 0:  25%|██▍       | 72/291 [00:00<00:01, 122.90it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:02, 68.69it/s] 
Loading 0:  34%|███▍      | 99/291 [00:01<00:02, 82.61it/s]
Loading 0:  38%|███▊      | 112/291 [00:01<00:01, 91.62it/s]
Loading 0:  43%|████▎     | 126/291 [00:01<00:01, 102.97it/s]
Loading 0:  48%|████▊     | 139/291 [00:01<00:01, 107.90it/s]
Loading 0:  53%|█████▎    | 153/291 [00:01<00:01, 116.09it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:01, 117.68it/s]
Loading 0:  62%|██████▏   | 180/291 [00:01<00:00, 123.47it/s]
Loading 0:  66%|██████▋   | 193/291 [00:02<00:01, 75.23it/s] 
Loading 0:  71%|███████   | 207/291 [00:02<00:00, 87.70it/s]
Loading 0:  76%|███████▌  | 220/291 [00:02<00:00, 95.22it/s]
Loading 0:  80%|████████  | 234/291 [00:02<00:00, 105.53it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 108.28it/s]
Loading 0:  90%|████████▉ | 261/291 [00:02<00:00, 115.96it/s]
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 116.79it/s]
Loading 0:  99%|█████████▊| 287/291 [00:08<00:00,  7.47it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v64-mkmlizer: quantized model in 24.847s
nousresearch-meta-llama-4941-v64-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 45.221s
nousresearch-meta-llama-4941-v64-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v64-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v64-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v64
nousresearch-meta-llama-4941-v64-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v64/config.json
nousresearch-meta-llama-4941-v64-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v64/special_tokens_map.json
nousresearch-meta-llama-4941-v64-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v64/tokenizer_config.json
nousresearch-meta-llama-4941-v64-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v64/tokenizer.json
nousresearch-meta-llama-4941-v64-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v64/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v64-mkmlizer: loading reward model from ChaiML/reward_models_100_170000000_cp_498032
nousresearch-meta-llama-4941-v64-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v64-mkmlizer:   warnings.warn(
nousresearch-meta-llama-4941-v64-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
nousresearch-meta-llama-4941-v64-mkmlizer:   warnings.warn(
nousresearch-meta-llama-4941-v64-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v64-mkmlizer:   warnings.warn(
Job nousresearch-meta-llama-4941-v64-mkmlizer completed after 80.11s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v64-mkmlizer
Pipeline stage MKMLizer completed in 82.05s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.44s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v64
Waiting for inference service nousresearch-meta-llama-4941-v64 to be ready
Inference service nousresearch-meta-llama-4941-v64 ready after 81.3673632144928s
Pipeline stage ISVCDeployer completed in 88.60s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0158891677856445s
Received healthy response to inference request in 1.2420039176940918s
Received healthy response to inference request in 1.2362151145935059s
Received healthy response to inference request in 1.234302043914795s
Received healthy response to inference request in 1.3383569717407227s
5 requests
0 failed requests
5th percentile: 1.234684658050537
10th percentile: 1.2350672721862792
20th percentile: 1.2358325004577637
30th percentile: 1.237372875213623
40th percentile: 1.2396883964538574
50th percentile: 1.2420039176940918
60th percentile: 1.280545139312744
70th percentile: 1.3190863609313965
80th percentile: 1.473863410949707
90th percentile: 1.744876289367676
95th percentile: 1.8803827285766601
99th percentile: 1.9887878799438476
mean time: 1.413353443145752
Pipeline stage StressChecker completed in 10.63s
nousresearch-meta-llama_4941_v64 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v64 status is now inactive due to admin request
admin requested tearing down of nousresearch-meta-llama_4941_v64
Running pipeline stage ISVCDeleter
Checking if service nousresearch-meta-llama-4941-v64 is running
Tearing down inference service nousresearch-meta-llama-4941-v64
Toredown service nousresearch-meta-llama-4941-v64
Pipeline stage ISVCDeleter completed in 12.24s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v64/config.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v64/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v64/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v64/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v64/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Running pipeline stage MKMLizer
Deleting key nousresearch-meta-llama-4941-v64_reward/config.json from bucket guanaco-reward-models
Starting job with name nousresearch-meta-llama-4941-v65-mkmlizer
Deleting key nousresearch-meta-llama-4941-v64_reward/merges.txt from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v64_reward/reward.tensors from bucket guanaco-reward-models
Waiting for job on nousresearch-meta-llama-4941-v65-mkmlizer to finish
Deleting key nousresearch-meta-llama-4941-v64_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v64_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v64_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v64_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.02s
nousresearch-meta-llama_4941_v64 status is now torndown due to DeploymentManager action