submission_id: nousresearch-meta-llama_4941_v65
developer_uid: end_to_end_test
status: torndown
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
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}
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}
reward_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}
timestamp: 2024-07-01T18:53:25+00:00
model_name: nousresearch-meta-llama_4941_v65
model_group: NousResearch/Meta-Llama-
num_battles: 390
num_wins: 179
celo_rating: None
propriety_score: 0.745945945945946
propriety_total_count: 185.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: nousresearch-meta-llama_4941_v65
ineligible_reason: propriety_total_count < 5000
language_model: NousResearch/Meta-Llama-3-8B-Instruct
model_size: 8B
reward_model: ChaiML/gpt2_xl_pairwise_89m_step_347634
us_pacific_date: 2024-07-01
win_ratio: 0.45897435897435895
Resubmit model
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
nousresearch-meta-llama-4941-v65-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v65-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ Version: 0.8.14 ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ https://mk1.ai ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-meta-llama-4941-v65-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v65-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v65-mkmlizer: Downloaded to shared memory in 23.373s
nousresearch-meta-llama-4941-v65-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v65-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v65-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 112.07it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:02, 121.74it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 120.34it/s] Loading 0: 19%|█▊ | 54/291 [00:00<00:01, 125.40it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 122.36it/s] Loading 0: 28%|██▊ | 81/291 [00:00<00:01, 126.32it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:02, 68.88it/s] Loading 0: 37%|███▋ | 107/291 [00:01<00:02, 80.60it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 90.17it/s] Loading 0: 46%|████▌ | 134/291 [00:01<00:01, 98.75it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 104.38it/s] Loading 0: 55%|█████▌ | 161/291 [00:01<00:01, 110.75it/s] Loading 0: 60%|██████ | 175/291 [00:01<00:00, 117.19it/s] Loading 0: 65%|██████▍ | 188/291 [00:02<00:01, 73.97it/s] Loading 0: 69%|██████▉ | 201/291 [00:02<00:01, 82.56it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:00, 86.30it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 101.56it/s] Loading 0: 82%|████████▏ | 240/291 [00:02<00:00, 103.10it/s] Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 113.13it/s] Loading 0: 92%|█████████▏| 268/291 [00:02<00:00, 112.29it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 114.10it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v65-mkmlizer: quantized model in 24.643s
nousresearch-meta-llama-4941-v65-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 48.016s
nousresearch-meta-llama-4941-v65-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v65-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v65-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v65
nousresearch-meta-llama-4941-v65-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v65/config.json
nousresearch-meta-llama-4941-v65-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v65/special_tokens_map.json
nousresearch-meta-llama-4941-v65-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v65/tokenizer_config.json
nousresearch-meta-llama-4941-v65-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v65/tokenizer.json
nousresearch-meta-llama-4941-v65-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v65/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v65-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-v65-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v65-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-v65-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v65-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:09<00:09, 9.33s/it] Downloading shards: 100%|██████████| 2/2 [00:14<00:00, 6.84s/it] Downloading shards: 100%|██████████| 2/2 [00:14<00:00, 7.21s/it]
nousresearch-meta-llama-4941-v65-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.58it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.77it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.48it/s]
nousresearch-meta-llama-4941-v65-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v65-mkmlizer: Saving duration: 1.678s
nousresearch-meta-llama-4941-v65-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 18.733s
nousresearch-meta-llama-4941-v65-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v65-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v65-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v65_reward
nousresearch-meta-llama-4941-v65-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v65_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v65-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v65_reward/config.json
nousresearch-meta-llama-4941-v65-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v65_reward/merges.txt
nousresearch-meta-llama-4941-v65-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v65_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v65-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v65_reward/vocab.json
nousresearch-meta-llama-4941-v65-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v65_reward/tokenizer.json
Job nousresearch-meta-llama-4941-v65-mkmlizer completed after 108.06s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v65-mkmlizer
Pipeline stage MKMLizer completed in 110.30s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.51s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v65
Waiting for inference service nousresearch-meta-llama-4941-v65 to be ready
Inference service nousresearch-meta-llama-4941-v65 ready after 132.0485360622406s
Pipeline stage ISVCDeployer completed in 138.81s
Running pipeline stage StressChecker
Received healthy response to inference request in 10.578927040100098s
Received healthy response to inference request in 1.399813175201416s
Received healthy response to inference request in 1.2930891513824463s
Received healthy response to inference request in 1.3151099681854248s
Received healthy response to inference request in 1.3280198574066162s
5 requests
0 failed requests
5th percentile: 1.297493314743042
10th percentile: 1.3018974781036377
20th percentile: 1.310705804824829
30th percentile: 1.317691946029663
40th percentile: 1.3228559017181396
50th percentile: 1.3280198574066162
60th percentile: 1.3567371845245362
70th percentile: 1.3854545116424561
80th percentile: 3.2356359481811543
90th percentile: 6.907281494140626
95th percentile: 8.74310426712036
99th percentile: 10.21176248550415
mean time: 3.1829918384552003
Pipeline stage StressChecker completed in 19.60s
nousresearch-meta-llama_4941_v65 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v65 status is now inactive due to admin request
admin requested tearing down of nousresearch-meta-llama_4941_v65
Running pipeline stage ISVCDeleter
Checking if service nousresearch-meta-llama-4941-v65 is running
Tearing down inference service nousresearch-meta-llama-4941-v65
Toredown service nousresearch-meta-llama-4941-v65
Pipeline stage ISVCDeleter completed in 7.77s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v65/config.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v65/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v65/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v65/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v65/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v65_reward/config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v65_reward/merges.txt from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v65_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v65_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v65_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v65_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v65_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.24s
nousresearch-meta-llama_4941_v65 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics