submission_id: nousresearch-meta-llama_4941_v75
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': 2, '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: 2024-07-03T18:24:58+00:00
model_name: nousresearch-meta-llama_4941_v75
model_group: NousResearch/Meta-Llama-
num_battles: 13942
num_wins: 6368
celo_rating: 1140.8
propriety_score: 0.7462529976019184
propriety_total_count: 6672.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 2
max_input_tokens: 512
max_output_tokens: 64
display_name: nousresearch-meta-llama_4941_v75
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: 0.45674939033137285
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v75-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v75-mkmlizer to finish
nousresearch-meta-llama-4941-v75-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v75-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ Version: 0.8.14 ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ https://mk1.ai ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-meta-llama-4941-v75-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v75-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v75-mkmlizer: Downloaded to shared memory in 22.694s
nousresearch-meta-llama-4941-v75-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v75-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v75-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 3%|▎ | 9/291 [00:00<00:03, 86.68it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:02, 94.96it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 89.53it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:02, 89.85it/s] Loading 0: 18%|█▊ | 53/291 [00:00<00:02, 97.74it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:02, 101.78it/s] Loading 0: 26%|██▋ | 77/291 [00:00<00:02, 93.53it/s] Loading 0: 30%|██▉ | 87/291 [00:01<00:04, 50.27it/s] Loading 0: 33%|███▎ | 97/291 [00:01<00:03, 58.61it/s] Loading 0: 37%|███▋ | 107/291 [00:01<00:02, 66.48it/s] Loading 0: 41%|████ | 120/291 [00:01<00:02, 78.70it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 82.18it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 86.04it/s] Loading 0: 53%|█████▎ | 155/291 [00:01<00:01, 102.64it/s] Loading 0: 57%|█████▋ | 167/291 [00:02<00:01, 95.64it/s] Loading 0: 62%|██████▏ | 181/291 [00:02<00:01, 102.44it/s] Loading 0: 66%|██████▌ | 192/291 [00:02<00:01, 64.12it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 69.61it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:01, 75.11it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 91.26it/s] Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 87.75it/s] Loading 0: 87%|████████▋ | 253/291 [00:03<00:00, 100.03it/s] Loading 0: 91%|█████████ | 264/291 [00:03<00:00, 102.54it/s] Loading 0: 95%|█████████▍| 275/291 [00:03<00:00, 98.79it/s] Loading 0: 99%|█████████▊| 287/291 [00:09<00:00, 6.45it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v75-mkmlizer: quantized model in 25.028s
nousresearch-meta-llama-4941-v75-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 47.723s
nousresearch-meta-llama-4941-v75-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v75/tokenizer_config.json
nousresearch-meta-llama-4941-v75-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v75/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v75-mkmlizer: loading reward model from ChaiML/gpt2_medium_pairwise_60m_step_937500
nousresearch-meta-llama-4941-v75-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-v75-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v75-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-v75-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v75-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-v75-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v75-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-v75-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v75-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v75-mkmlizer: Saving duration: 0.428s
nousresearch-meta-llama-4941-v75-mkmlizer: Processed model ChaiML/gpt2_medium_pairwise_60m_step_937500 in 4.010s
nousresearch-meta-llama-4941-v75-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-4941-v75_reward/reward.tensors
Job nousresearch-meta-llama-4941-v75-mkmlizer completed after 73.22s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v75-mkmlizer
Pipeline stage MKMLizer completed in 74.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v75
Waiting for inference service nousresearch-meta-llama-4941-v75 to be ready
Inference service nousresearch-meta-llama-4941-v75 ready after 90.48949098587036s
Pipeline stage ISVCDeployer completed in 97.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9815738201141357s
Received healthy response to inference request in 1.1099205017089844s
Received healthy response to inference request in 0.9513864517211914s
Received healthy response to inference request in 0.8877058029174805s
Received healthy response to inference request in 0.718665599822998s
5 requests
0 failed requests
5th percentile: 0.7524736404418946
10th percentile: 0.786281681060791
20th percentile: 0.8538977622985839
30th percentile: 0.9004419326782227
40th percentile: 0.925914192199707
50th percentile: 0.9513864517211914
60th percentile: 1.0148000717163086
70th percentile: 1.0782136917114258
80th percentile: 1.2842511653900148
90th percentile: 1.6329124927520753
95th percentile: 1.8072431564331053
99th percentile: 1.9467076873779297
mean time: 1.129850435256958
Pipeline stage StressChecker completed in 6.27s
nousresearch-meta-llama_4941_v75 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v75 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics