submission_id: nousresearch-meta-llama_4941_v49
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': 1024, 'best_of': 4, 'max_output_tokens': 300}
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: 2024-04-29T14:03:59+00:00
model_name: nousresearch-meta-llama_4941_v49
model_eval_status: pending
double_thumbs_up: 0
thumbs_up: 0
thumbs_down: 0
num_battles: 0
num_wins: 0
celo_rating: None
entertaining: None
stay_in_character: None
user_preference: None
safety_score: 0.94
submission_type: basic
model_architecture: None
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 300
display_name: nousresearch-meta-llama_4941_v49
double_thumbs_up_ratio: None
feedback_count: 0
ineligible_reason: max_output_tokens!=64
language_model: NousResearch/Meta-Llama-3-8B-Instruct
model_score: None
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: None
thumbs_down_ratio: None
thumbs_up_ratio: None
us_pacific_date: 2024-04-29
win_ratio: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v49-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v49-mkmlizer to finish
nousresearch-meta-llama-4941-v49-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v49-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ Version: 0.8.10 ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nousresearch-meta-llama-4941-v49-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v49-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v49-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
nousresearch-meta-llama-4941-v49-mkmlizer: warnings.warn(warning_message, FutureWarning)
nousresearch-meta-llama-4941-v49-mkmlizer: Downloaded to shared memory in 17.360s
nousresearch-meta-llama-4941-v49-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v49-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v49-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 137.64it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 37.76it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v49-mkmlizer: quantized model in 17.192s
nousresearch-meta-llama-4941-v49-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 35.590s
nousresearch-meta-llama-4941-v49-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v49-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v49-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v49
nousresearch-meta-llama-4941-v49-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v49/config.json
nousresearch-meta-llama-4941-v49-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v49/tokenizer_config.json
nousresearch-meta-llama-4941-v49-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v49/special_tokens_map.json
nousresearch-meta-llama-4941-v49-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v49/tokenizer.json
nousresearch-meta-llama-4941-v49-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nousresearch-meta-llama-4941-v49-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v49-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v49-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v49-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v49-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-v49-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v49-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-v49-mkmlizer: return self.fget.__get__(instance, owner)()
nousresearch-meta-llama-4941-v49-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v49-mkmlizer: Saving duration: 0.247s
nousresearch-meta-llama-4941-v49-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.451s
nousresearch-meta-llama-4941-v49-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v49-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v49-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v49_reward
nousresearch-meta-llama-4941-v49-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v49_reward/config.json
nousresearch-meta-llama-4941-v49-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v49_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v49-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v49_reward/merges.txt
nousresearch-meta-llama-4941-v49-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v49_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v49-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v49_reward/vocab.json
nousresearch-meta-llama-4941-v49-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v49_reward/tokenizer.json
nousresearch-meta-llama-4941-v49-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-4941-v49_reward/reward.tensors
Job nousresearch-meta-llama-4941-v49-mkmlizer completed after 71.19s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v49-mkmlizer
Pipeline stage MKMLizer completed in 72.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.39s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v49
Waiting for inference service nousresearch-meta-llama-4941-v49 to be ready
Inference service nousresearch-meta-llama-4941-v49 ready after 40.59882426261902s
Pipeline stage ISVCDeployer completed in 47.54s
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 3.402039051055908s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.6413283348083496s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.637434482574463s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.6577765941619873s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.6270115375518799s
5 requests
0 failed requests
5th percentile: 1.6290961265563966
10th percentile: 1.631180715560913
20th percentile: 1.6353498935699462
30th percentile: 1.6382132530212403
40th percentile: 1.639770793914795
50th percentile: 1.6413283348083496
60th percentile: 1.6479076385498046
70th percentile: 1.6544869422912598
80th percentile: 2.006629085540772
90th percentile: 2.70433406829834
95th percentile: 3.0531865596771235
99th percentile: 3.3322685527801514
mean time: 1.9931180000305175
Pipeline stage StressChecker completed in 13.81s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.19s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.31s
nousresearch-meta-llama_4941_v49 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v49 status is now inactive due to admin request

Usage Metrics

Latency Metrics