submission_id: nousresearch-meta-llama_4941_v59
developer_uid: chai_backend_admin
status: inactive
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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'], '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': "{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}
timestamp: 2024-06-27T19:27:57+00:00
model_name: nousresearch-meta-llama_4941_v59
model_group: NousResearch/Meta-Llama-
num_battles: 17757
num_wins: 8500
celo_rating: 1172.87
propriety_score: 0.7301139701562683
propriety_total_count: 8511.0
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_v59
ineligible_reason: None
language_model: NousResearch/Meta-Llama-3-8B-Instruct
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-27
win_ratio: 0.47868446246550655
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v59-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v59-mkmlizer to finish
nousresearch-meta-llama-4941-v59-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v59-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ Version: 0.8.14 ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ https://mk1.ai ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v59-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v59-mkmlizer: Downloaded to shared memory in 55.168s
nousresearch-meta-llama-4941-v59-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v59-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v59-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 3%|▎ | 8/291 [00:00<00:03, 75.76it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:03, 78.03it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:03, 77.71it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:02, 97.47it/s] Loading 0: 16%|█▌ | 47/291 [00:00<00:02, 97.11it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:02, 91.34it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 90.01it/s] Loading 0: 26%|██▋ | 77/291 [00:00<00:02, 84.98it/s] Loading 0: 30%|██▉ | 86/291 [00:01<00:05, 37.66it/s] Loading 0: 34%|███▍ | 99/291 [00:01<00:03, 51.03it/s] Loading 0: 38%|███▊ | 111/291 [00:01<00:02, 60.29it/s] Loading 0: 41%|████ | 120/291 [00:01<00:02, 65.60it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:02, 70.63it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:02, 74.70it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:01, 80.10it/s] Loading 0: 54%|█████▍ | 157/291 [00:02<00:01, 82.15it/s] Loading 0: 57%|█████▋ | 166/291 [00:02<00:01, 83.81it/s] Loading 0: 62%|██████▏ | 179/291 [00:02<00:01, 91.06it/s] Loading 0: 65%|██████▍ | 189/291 [00:02<00:02, 43.88it/s] Loading 0: 68%|██████▊ | 198/291 [00:03<00:01, 50.62it/s] Loading 0: 71%|███████ | 207/291 [00:03<00:01, 57.34it/s] Loading 0: 75%|███████▍ | 217/291 [00:03<00:01, 65.74it/s] Loading 0: 78%|███████▊ | 226/291 [00:03<00:00, 70.95it/s] Loading 0: 81%|████████ | 235/291 [00:03<00:00, 75.45it/s] Loading 0: 85%|████████▍ | 246/291 [00:03<00:00, 82.14it/s] Loading 0: 88%|████████▊ | 256/291 [00:03<00:00, 82.69it/s] Loading 0: 91%|█████████ | 265/291 [00:03<00:00, 84.06it/s] Loading 0: 94%|█████████▍| 274/291 [00:03<00:00, 85.51it/s] Loading 0: 97%|█████████▋| 283/291 [00:03<00:00, 85.85it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v59-mkmlizer: quantized model in 26.315s
nousresearch-meta-llama-4941-v59-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 81.483s
nousresearch-meta-llama-4941-v59-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v59-mkmlizer: ERROR: [Errno -3] Temporary failure in name resolution
nousresearch-meta-llama-4941-v59-mkmlizer: ERROR: Connection Error: Error resolving a server hostname.
nousresearch-meta-llama-4941-v59-mkmlizer: Please check the servers address specified in 'host_base', 'host_bucket', 'cloudfront_host', 'website_endpoint'
Job nousresearch-meta-llama-4941-v59-mkmlizer completed after 102.57s with status: failed
Stopping job with name nousresearch-meta-llama-4941-v59-mkmlizer
%s, retrying in %s seconds...
Starting job with name nousresearch-meta-llama-4941-v59-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v59-mkmlizer to finish
nousresearch-meta-llama-4941-v59-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v59-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ Version: 0.8.14 ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ https://mk1.ai ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-meta-llama-4941-v59-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v59-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v59-mkmlizer: Downloaded to shared memory in 24.683s
nousresearch-meta-llama-4941-v59-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v59-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v59-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:01, 139.45it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 154.41it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 157.82it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 146.81it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 82.88it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 86.19it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:01, 102.71it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 116.59it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 127.70it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:00, 137.31it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 139.64it/s] Loading 0: 67%|██████▋ | 195/291 [00:01<00:01, 85.97it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 100.30it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 115.12it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 126.49it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 136.54it/s] Loading 0: 98%|█████████▊| 285/291 [00:02<00:00, 148.73it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v59-mkmlizer: quantized model in 23.095s
nousresearch-meta-llama-4941-v59-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 47.778s
nousresearch-meta-llama-4941-v59-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v59-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v59-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v59
nousresearch-meta-llama-4941-v59-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v59/config.json
nousresearch-meta-llama-4941-v59-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v59/special_tokens_map.json
nousresearch-meta-llama-4941-v59-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v59/tokenizer_config.json
nousresearch-meta-llama-4941-v59-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v59/tokenizer.json
nousresearch-meta-llama-4941-v59-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nousresearch-meta-llama-4941-v59-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-v59-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v59-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-v59-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v59-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-v59-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v59-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-v59-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v59-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
nousresearch-meta-llama-4941-v59-mkmlizer: return self.fget.__get__(instance, owner)()
nousresearch-meta-llama-4941-v59-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v59-mkmlizer: Saving duration: 0.391s
nousresearch-meta-llama-4941-v59-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.784s
nousresearch-meta-llama-4941-v59-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v59-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v59-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v59_reward
nousresearch-meta-llama-4941-v59-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v59_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v59-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v59_reward/config.json
nousresearch-meta-llama-4941-v59-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v59_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v59-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v59_reward/merges.txt
nousresearch-meta-llama-4941-v59-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v59_reward/vocab.json
nousresearch-meta-llama-4941-v59-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v59_reward/tokenizer.json
nousresearch-meta-llama-4941-v59-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-4941-v59_reward/reward.tensors
Job nousresearch-meta-llama-4941-v59-mkmlizer completed after 129.04s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v59-mkmlizer
Pipeline stage MKMLizer completed in 236.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.58s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v59
Waiting for inference service nousresearch-meta-llama-4941-v59 to be ready
Inference service nousresearch-meta-llama-4941-v59 ready after 41.3888041973114s
Pipeline stage ISVCDeployer completed in 43.17s
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.7315399646759033s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.7538859844207764s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.479489803314209s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.8294970989227295s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.7207541465759277s
5 requests
0 failed requests
5th percentile: 1.7273805141448975
10th percentile: 1.7340068817138672
20th percentile: 1.7472596168518066
30th percentile: 1.8990067481994628
40th percentile: 2.189248275756836
50th percentile: 2.479489803314209
60th percentile: 2.5803098678588867
70th percentile: 2.6811299324035645
80th percentile: 2.7511313915252686
90th percentile: 2.790314245223999
95th percentile: 2.809905672073364
99th percentile: 2.8255788135528563
mean time: 2.303033399581909
Pipeline stage StressChecker completed in 15.68s
nousresearch-meta-llama_4941_v59 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v59 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics