submission_id: hastagaras-esekembrew-ll_1360_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/esekembrew-llama3-8b
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: 2024-05-17T08:22:05+00:00
model_name: mweheh
model_eval_status: success
model_group: Hastagaras/esekembrew-ll
num_battles: 16944
num_wins: 9036
celo_rating: 1198.66
safety_score: 0.97
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: mweheh
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/esekembrew-llama3-8b
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-17
win_ratio: 0.53328611898017
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-esekembrew-ll-1360-v1-mkmlizer
Waiting for job on hastagaras-esekembrew-ll-1360-v1-mkmlizer to finish
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ /___/ ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ belonging to: ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ║ ║
hastagaras-esekembrew-ll-1360-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekembrew-ll-1360-v1-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.
hastagaras-esekembrew-ll-1360-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-esekembrew-ll-1360-v1-mkmlizer: Downloaded to shared memory in 27.865s
hastagaras-esekembrew-ll-1360-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekembrew-ll-1360-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekembrew-ll-1360-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 111.11it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 93.45it/s] Loading 0: 12%|█▏ | 35/291 [00:00<00:02, 99.62it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:02, 104.44it/s] Loading 0: 20%|██ | 59/291 [00:00<00:02, 98.29it/s] Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 113.47it/s] Loading 0: 30%|██▉ | 87/291 [00:01<00:03, 52.85it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:03, 62.03it/s] Loading 0: 38%|███▊ | 111/291 [00:01<00:02, 72.79it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:02, 78.04it/s] Loading 0: 46%|████▋ | 135/291 [00:01<00:01, 90.85it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 96.39it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 111.10it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 116.90it/s] Loading 0: 66%|██████▌ | 192/291 [00:02<00:01, 63.22it/s] Loading 0: 70%|██████▉ | 203/291 [00:02<00:01, 68.97it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 83.24it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 86.54it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 100.15it/s] Loading 0: 89%|████████▊ | 258/291 [00:02<00:00, 100.89it/s] Loading 0: 94%|█████████▍| 273/291 [00:03<00:00, 112.25it/s] Loading 0: 98%|█████████▊| 286/291 [00:03<00:00, 116.19it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekembrew-ll-1360-v1-mkmlizer: quantized model in 21.698s
hastagaras-esekembrew-ll-1360-v1-mkmlizer: Processed model Hastagaras/esekembrew-llama3-8b in 50.738s
hastagaras-esekembrew-ll-1360-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekembrew-ll-1360-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekembrew-ll-1360-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v1
hastagaras-esekembrew-ll-1360-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v1/config.json
hastagaras-esekembrew-ll-1360-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v1/special_tokens_map.json
hastagaras-esekembrew-ll-1360-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v1/tokenizer_config.json
hastagaras-esekembrew-ll-1360-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v1/tokenizer.json
hastagaras-esekembrew-ll-1360-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-esekembrew-ll-1360-v1/flywheel_model.0.safetensors
hastagaras-esekembrew-ll-1360-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekembrew-ll-1360-v1-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.
hastagaras-esekembrew-ll-1360-v1-mkmlizer: warnings.warn(
hastagaras-esekembrew-ll-1360-v1-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.
hastagaras-esekembrew-ll-1360-v1-mkmlizer: warnings.warn(
hastagaras-esekembrew-ll-1360-v1-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()
hastagaras-esekembrew-ll-1360-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-esekembrew-ll-1360-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekembrew-ll-1360-v1-mkmlizer: Saving duration: 0.283s
hastagaras-esekembrew-ll-1360-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.175s
hastagaras-esekembrew-ll-1360-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-esekembrew-ll-1360-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekembrew-ll-1360-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v1_reward
hastagaras-esekembrew-ll-1360-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v1_reward/special_tokens_map.json
hastagaras-esekembrew-ll-1360-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v1_reward/config.json
hastagaras-esekembrew-ll-1360-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v1_reward/tokenizer_config.json
hastagaras-esekembrew-ll-1360-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v1_reward/merges.txt
hastagaras-esekembrew-ll-1360-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v1_reward/vocab.json
hastagaras-esekembrew-ll-1360-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v1_reward/tokenizer.json
hastagaras-esekembrew-ll-1360-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-esekembrew-ll-1360-v1_reward/reward.tensors
Job hastagaras-esekembrew-ll-1360-v1-mkmlizer completed after 82.84s with status: succeeded
Stopping job with name hastagaras-esekembrew-ll-1360-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.38s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekembrew-ll-1360-v1
Waiting for inference service hastagaras-esekembrew-ll-1360-v1 to be ready
Inference service hastagaras-esekembrew-ll-1360-v1 ready after 50.24839687347412s
Pipeline stage ISVCDeployer completed in 57.30s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2161169052124023s
Received healthy response to inference request in 1.2616713047027588s
Received healthy response to inference request in 1.2649266719818115s
Received healthy response to inference request in 1.2770683765411377s
Received healthy response to inference request in 1.2651605606079102s
5 requests
0 failed requests
5th percentile: 1.2623223781585693
10th percentile: 1.2629734516143798
20th percentile: 1.264275598526001
30th percentile: 1.2649734497070313
40th percentile: 1.2650670051574706
50th percentile: 1.2651605606079102
60th percentile: 1.2699236869812012
70th percentile: 1.2746868133544922
80th percentile: 1.4648780822753908
90th percentile: 1.8404974937438965
95th percentile: 2.0283071994781494
99th percentile: 2.178554964065552
mean time: 1.456988763809204
Pipeline stage StressChecker completed in 7.93s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-esekembrew-ll_1360_v1 status is now deployed due to DeploymentManager action
hastagaras-esekembrew-ll_1360_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics