submission_id: nousresearch-meta-llama_4941_v79
developer_uid: zonemercy
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': ['\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: 2024-07-09T16:30:43+00:00
model_name: nousresearch-meta-llama_4941_v79
model_group: NousResearch/Meta-Llama-
num_battles: 29960
num_wins: 14538
celo_rating: 1185.14
alignment_score: None
alignment_samples: 0
propriety_score: 0.714975845410628
propriety_total_count: 5175.0
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_v79
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: 2024-07-09
win_ratio: 0.48524699599465954
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v79-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v79-mkmlizer to finish
nousresearch-meta-llama-4941-v79-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v79-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ Version: 0.8.14 ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ https://mk1.ai ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-meta-llama-4941-v79-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v79-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v79-mkmlizer: Downloaded to shared memory in 25.498s
nousresearch-meta-llama-4941-v79-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v79-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v79-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 120.91it/s] Loading 0: 10%|▉ | 28/291 [00:00<00:01, 137.31it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:01, 125.81it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:01, 134.69it/s] Loading 0: 24%|██▍ | 71/291 [00:00<00:01, 131.38it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:03, 60.47it/s] Loading 0: 34%|███▍ | 100/291 [00:01<00:02, 75.67it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 83.73it/s] Loading 0: 44%|████▎ | 127/291 [00:01<00:01, 97.95it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 99.23it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 113.51it/s] Loading 0: 58%|█████▊ | 170/291 [00:01<00:01, 116.69it/s] Loading 0: 63%|██████▎ | 184/291 [00:01<00:00, 121.81it/s] Loading 0: 68%|██████▊ | 198/291 [00:02<00:01, 64.60it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 74.70it/s] Loading 0: 78%|███████▊ | 226/291 [00:02<00:00, 88.92it/s] Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 92.93it/s] Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 107.96it/s] Loading 0: 92%|█████████▏| 268/291 [00:02<00:00, 111.72it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 113.62it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v79-mkmlizer: quantized model in 28.691s
nousresearch-meta-llama-4941-v79-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 54.189s
nousresearch-meta-llama-4941-v79-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v79-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v79-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v79
nousresearch-meta-llama-4941-v79-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v79/tokenizer_config.json
nousresearch-meta-llama-4941-v79-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v79/special_tokens_map.json
nousresearch-meta-llama-4941-v79-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v79/config.json
nousresearch-meta-llama-4941-v79-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v79/tokenizer.json
nousresearch-meta-llama-4941-v79-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v79/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v79-mkmlizer: loading reward model from ChaiML/gpt2_medium_pairwise_60m_step_937500
nousresearch-meta-llama-4941-v79-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-v79-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v79-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-v79-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v79-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-v79-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v79-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-v79-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v79-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v79-mkmlizer: Saving duration: 0.514s
nousresearch-meta-llama-4941-v79-mkmlizer: Processed model ChaiML/gpt2_medium_pairwise_60m_step_937500 in 7.080s
nousresearch-meta-llama-4941-v79-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v79-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v79-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v79_reward
nousresearch-meta-llama-4941-v79-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v79_reward/config.json
nousresearch-meta-llama-4941-v79-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v79_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v79-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v79_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v79-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v79_reward/merges.txt
nousresearch-meta-llama-4941-v79-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v79_reward/vocab.json
nousresearch-meta-llama-4941-v79-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v79_reward/tokenizer.json
nousresearch-meta-llama-4941-v79-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-4941-v79_reward/reward.tensors
Job nousresearch-meta-llama-4941-v79-mkmlizer completed after 96.03s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v79-mkmlizer
Pipeline stage MKMLizer completed in 97.18s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v79
Waiting for inference service nousresearch-meta-llama-4941-v79 to be ready
Inference service nousresearch-meta-llama-4941-v79 ready after 30.167686223983765s
Pipeline stage ISVCDeployer completed in 37.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9774188995361328s
Received healthy response to inference request in 1.2632942199707031s
Received healthy response to inference request in 1.2630486488342285s
Received healthy response to inference request in 1.2505717277526855s
Received healthy response to inference request in 1.2249257564544678s
5 requests
0 failed requests
5th percentile: 1.2300549507141114
10th percentile: 1.2351841449737548
20th percentile: 1.245442533493042
30th percentile: 1.2530671119689942
40th percentile: 1.2580578804016114
50th percentile: 1.2630486488342285
60th percentile: 1.2631468772888184
70th percentile: 1.2632451057434082
80th percentile: 1.406119155883789
90th percentile: 1.691769027709961
95th percentile: 1.8345939636230468
99th percentile: 1.9488539123535156
mean time: 1.3958518505096436
Pipeline stage StressChecker completed in 7.89s
nousresearch-meta-llama_4941_v79 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v79 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics