submission_id: nousresearch-meta-llama_4941_v74
developer_uid: robert_irvine
status: inactive
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
reward_repo: ChaiML/gpt2_medium_pairwise_60m_step_937500
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': ['</s>', '<|user|>', '###', '\n'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64}
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}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-07-03T18:24:01+00:00
model_name: nousresearch-meta-llama_4941_v74
model_group: NousResearch/Meta-Llama-
num_battles: 13818
num_wins: 5709
celo_rating: 1110.98
propriety_score: 0.7507344982217411
propriety_total_count: 6467.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
display_name: nousresearch-meta-llama_4941_v74
ineligible_reason: None
language_model: NousResearch/Meta-Llama-3-8B-Instruct
model_size: 8B
reward_model: ChaiML/gpt2_medium_pairwise_60m_step_937500
us_pacific_date: 2024-07-03
win_ratio: 0.41315675206252717
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v74-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v74-mkmlizer to finish
nousresearch-meta-llama-4941-v74-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v74-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ Version: 0.8.14 ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ https://mk1.ai ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-meta-llama-4941-v74-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v74-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v74-mkmlizer: Downloaded to shared memory in 19.903s
nousresearch-meta-llama-4941-v74-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v74-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v74-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 3%|▎ | 8/291 [00:00<00:03, 79.19it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:02, 106.85it/s] Loading 0: 11%|█ | 32/291 [00:00<00:02, 100.26it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:02, 115.72it/s] Loading 0: 21%|██ | 60/291 [00:00<00:02, 101.40it/s] Loading 0: 24%|██▍ | 71/291 [00:00<00:02, 102.68it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 59.64it/s] Loading 0: 32%|███▏ | 93/291 [00:01<00:02, 66.85it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 71.92it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:02, 74.76it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:02, 77.25it/s] Loading 0: 46%|████▋ | 135/291 [00:01<00:01, 89.78it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 95.40it/s] Loading 0: 55%|█████▍ | 159/291 [00:01<00:01, 99.13it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:01, 105.57it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 65.74it/s] Loading 0: 67%|██████▋ | 196/291 [00:02<00:01, 64.48it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:01, 66.78it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:01, 68.26it/s] Loading 0: 76%|███████▌ | 221/291 [00:02<00:00, 71.41it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 75.90it/s] Loading 0: 85%|████████▍ | 246/291 [00:03<00:00, 93.59it/s] Loading 0: 88%|████████▊ | 256/291 [00:03<00:00, 95.01it/s] Loading 0: 91%|█████████▏| 266/291 [00:03<00:00, 95.50it/s] Loading 0: 97%|█████████▋| 281/291 [00:03<00:00, 105.32it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v74-mkmlizer: quantized model in 26.760s
nousresearch-meta-llama-4941-v74-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 46.664s
nousresearch-meta-llama-4941-v74-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v74-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v74-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v74
nousresearch-meta-llama-4941-v74-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v74/tokenizer_config.json
nousresearch-meta-llama-4941-v74-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v74/config.json
nousresearch-meta-llama-4941-v74-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v74/special_tokens_map.json
nousresearch-meta-llama-4941-v74-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v74/tokenizer.json
nousresearch-meta-llama-4941-v74-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v74/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v74-mkmlizer: loading reward model from ChaiML/gpt2_medium_pairwise_60m_step_937500
nousresearch-meta-llama-4941-v74-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-v74-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v74-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-v74-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v74-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-v74-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v74-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v74-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v74-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
Job nousresearch-meta-llama-4941-v74-mkmlizer completed after 74.91s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v74-mkmlizer
Pipeline stage MKMLizer completed in 76.05s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v74
Waiting for inference service nousresearch-meta-llama-4941-v74 to be ready
Inference service nousresearch-meta-llama-4941-v74 ready after 40.2250440120697s
Pipeline stage ISVCDeployer completed in 47.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9429450035095215s
Received healthy response to inference request in 0.9025180339813232s
Received healthy response to inference request in 1.059030294418335s
Received healthy response to inference request in 0.4200437068939209s
Received healthy response to inference request in 0.7836804389953613s
5 requests
0 failed requests
5th percentile: 0.492771053314209
10th percentile: 0.5654983997344971
20th percentile: 0.7109530925750732
30th percentile: 0.8074479579925538
40th percentile: 0.8549829959869385
50th percentile: 0.9025180339813232
60th percentile: 0.9651229381561279
70th percentile: 1.0277278423309326
80th percentile: 1.2358132362365724
90th percentile: 1.589379119873047
95th percentile: 1.766162061691284
99th percentile: 1.907588415145874
mean time: 1.0216434955596925
Pipeline stage StressChecker completed in 5.84s
nousresearch-meta-llama_4941_v74 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v74 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics