submission_id: nousresearch-meta-llama_4941_v80
developer_uid: zonemercy
status: inactive
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
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', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 16, '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: 2024-07-09T16:32:44+00:00
model_name: nousresearch-meta-llama_4941_v80
model_group: NousResearch/Meta-Llama-
num_battles: 33253
num_wins: 16791
celo_rating: 1198.0
propriety_score: 0.7319288049400654
propriety_total_count: 5506.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nousresearch-meta-llama_4941_v80
ineligible_reason: None
language_model: NousResearch/Meta-Llama-3-8B-Instruct
model_size: 8B
reward_model: ChaiML/gpt2_xl_pairwise_89m_step_347634
us_pacific_date: 2024-07-09
win_ratio: 0.5049469220822181
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v80-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v80-mkmlizer to finish
nousresearch-meta-llama-4941-v80-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v80-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ Version: 0.8.14 ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ https://mk1.ai ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-meta-llama-4941-v80-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v80-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v80-mkmlizer: Downloaded to shared memory in 22.723s
nousresearch-meta-llama-4941-v80-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v80-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v80-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 117.68it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:02, 129.99it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:02, 121.12it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:01, 134.19it/s] Loading 0: 24%|██▍ | 71/291 [00:00<00:01, 129.68it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:03, 59.56it/s] Loading 0: 34%|███▍ | 99/291 [00:01<00:02, 73.05it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 83.00it/s] Loading 0: 43%|████▎ | 126/291 [00:01<00:01, 94.63it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 101.24it/s] Loading 0: 53%|█████▎ | 153/291 [00:01<00:01, 110.57it/s] Loading 0: 57%|█████▋ | 166/291 [00:01<00:01, 113.57it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 117.06it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 59.89it/s] Loading 0: 71%|███████▏ | 208/291 [00:02<00:01, 74.33it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 82.39it/s] Loading 0: 81%|████████ | 235/291 [00:02<00:00, 96.42it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 98.46it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 112.70it/s] Loading 0: 95%|█████████▌| 277/291 [00:02<00:00, 115.26it/s] Loading 0: 100%|█████████▉| 290/291 [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-v80-mkmlizer: quantized model in 28.791s
nousresearch-meta-llama-4941-v80-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 51.515s
nousresearch-meta-llama-4941-v80-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v80-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v80-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v80
nousresearch-meta-llama-4941-v80-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v80/config.json
nousresearch-meta-llama-4941-v80-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v80/tokenizer_config.json
nousresearch-meta-llama-4941-v80-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v80/special_tokens_map.json
nousresearch-meta-llama-4941-v80-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v80/tokenizer.json
nousresearch-meta-llama-4941-v80-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v80/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v80-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
nousresearch-meta-llama-4941-v80-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-v80-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v80-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-v80-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v80-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-v80-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v80-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-v80-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v80-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.82s/it] Downloading shards: 100%|██████████| 2/2 [00:10<00:00, 4.51s/it] Downloading shards: 100%|██████████| 2/2 [00:10<00:00, 5.00s/it]
nousresearch-meta-llama-4941-v80-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.66it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.73it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.49it/s]
nousresearch-meta-llama-4941-v80-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v80-mkmlizer: Saving duration: 2.184s
nousresearch-meta-llama-4941-v80-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.414s
nousresearch-meta-llama-4941-v80-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v80-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v80-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v80_reward
nousresearch-meta-llama-4941-v80-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v80_reward/config.json
nousresearch-meta-llama-4941-v80-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v80_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v80-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v80_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v80-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v80_reward/merges.txt
nousresearch-meta-llama-4941-v80-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v80_reward/vocab.json
nousresearch-meta-llama-4941-v80-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v80_reward/tokenizer.json
nousresearch-meta-llama-4941-v80-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-4941-v80_reward/reward.tensors
Job nousresearch-meta-llama-4941-v80-mkmlizer completed after 114.72s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v80-mkmlizer
Pipeline stage MKMLizer completed in 115.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v80
Waiting for inference service nousresearch-meta-llama-4941-v80 to be ready
Inference service nousresearch-meta-llama-4941-v80 ready after 70.34350490570068s
Pipeline stage ISVCDeployer completed in 77.59s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.409365177154541s
Received healthy response to inference request in 1.5088450908660889s
Received healthy response to inference request in 1.5028164386749268s
Received healthy response to inference request in 1.4814105033874512s
Received healthy response to inference request in 1.4915387630462646s
5 requests
0 failed requests
5th percentile: 1.483436155319214
10th percentile: 1.4854618072509767
20th percentile: 1.489513111114502
30th percentile: 1.4937942981719972
40th percentile: 1.498305368423462
50th percentile: 1.5028164386749268
60th percentile: 1.5052278995513917
70th percentile: 1.5076393604278564
80th percentile: 1.6889491081237795
90th percentile: 2.04915714263916
95th percentile: 2.2292611598968506
99th percentile: 2.373344373703003
mean time: 1.6787951946258546
Pipeline stage StressChecker completed in 9.16s
nousresearch-meta-llama_4941_v80 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v80 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics