submission_id: hastagaras-esekembrew-8b_2768_v1
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/Esekembrew-8B-Llama3-0.4
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 100, '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': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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: 2024-06-04T03:15:13+00:00
model_name: esk
model_eval_status: success
model_group: Hastagaras/Esekembrew-8B
num_battles: 18171
num_wins: 9992
celo_rating: 1204.05
propriety_score: 0.6516393442622951
propriety_total_count: 488.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: esk
ineligible_reason: propriety_total_count < 800
language_model: Hastagaras/Esekembrew-8B-Llama3-0.4
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-03
win_ratio: 0.5498871828738099
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-esekembrew-8b-2768-v1-mkmlizer
Waiting for job on hastagaras-esekembrew-8b-2768-v1-mkmlizer to finish
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ /___/ ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ belonging to: ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ║ ║
hastagaras-esekembrew-8b-2768-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekembrew-8b-2768-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-8b-2768-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-esekembrew-8b-2768-v1-mkmlizer: Downloaded to shared memory in 35.066s
hastagaras-esekembrew-8b-2768-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekembrew-8b-2768-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekembrew-8b-2768-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 123.91it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 147.88it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 155.97it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 159.08it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 86.67it/s] Loading 0: 34%|███▎ | 98/291 [00:00<00:01, 99.52it/s] Loading 0: 39%|███▉ | 114/291 [00:00<00:01, 113.26it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 125.70it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 136.88it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 146.63it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 98.82it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 106.16it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 120.30it/s] Loading 0: 82%|████████▏ | 238/291 [00:01<00:00, 132.95it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 143.45it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 151.73it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 10.11it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekembrew-8b-2768-v1-mkmlizer: quantized model in 22.773s
hastagaras-esekembrew-8b-2768-v1-mkmlizer: Processed model Hastagaras/Esekembrew-8B-Llama3-0.4 in 60.404s
hastagaras-esekembrew-8b-2768-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekembrew-8b-2768-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekembrew-8b-2768-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekembrew-8b-2768-v1
hastagaras-esekembrew-8b-2768-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-2768-v1/config.json
hastagaras-esekembrew-8b-2768-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-2768-v1/special_tokens_map.json
hastagaras-esekembrew-8b-2768-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-2768-v1/tokenizer_config.json
hastagaras-esekembrew-8b-2768-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-2768-v1/tokenizer.json
hastagaras-esekembrew-8b-2768-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-esekembrew-8b-2768-v1/flywheel_model.0.safetensors
hastagaras-esekembrew-8b-2768-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekembrew-8b-2768-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-8b-2768-v1-mkmlizer: warnings.warn(
hastagaras-esekembrew-8b-2768-v1-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.
hastagaras-esekembrew-8b-2768-v1-mkmlizer: warnings.warn(
hastagaras-esekembrew-8b-2768-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-8b-2768-v1-mkmlizer: warnings.warn(
hastagaras-esekembrew-8b-2768-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-8b-2768-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-esekembrew-8b-2768-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekembrew-8b-2768-v1-mkmlizer: Saving duration: 0.395s
hastagaras-esekembrew-8b-2768-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.586s
hastagaras-esekembrew-8b-2768-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-esekembrew-8b-2768-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekembrew-8b-2768-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekembrew-8b-2768-v1_reward
hastagaras-esekembrew-8b-2768-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-2768-v1_reward/config.json
hastagaras-esekembrew-8b-2768-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-2768-v1_reward/tokenizer_config.json
hastagaras-esekembrew-8b-2768-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekembrew-8b-2768-v1_reward/merges.txt
hastagaras-esekembrew-8b-2768-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-2768-v1_reward/vocab.json
hastagaras-esekembrew-8b-2768-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-2768-v1_reward/special_tokens_map.json
hastagaras-esekembrew-8b-2768-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-2768-v1_reward/tokenizer.json
hastagaras-esekembrew-8b-2768-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-esekembrew-8b-2768-v1_reward/reward.tensors
Job hastagaras-esekembrew-8b-2768-v1-mkmlizer completed after 83.79s with status: succeeded
Stopping job with name hastagaras-esekembrew-8b-2768-v1-mkmlizer
Pipeline stage MKMLizer completed in 88.62s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekembrew-8b-2768-v1
Waiting for inference service hastagaras-esekembrew-8b-2768-v1 to be ready
Inference service hastagaras-esekembrew-8b-2768-v1 ready after 40.32067060470581s
Pipeline stage ISVCDeployer completed in 48.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1741015911102295s
Received healthy response to inference request in 1.3271312713623047s
Received healthy response to inference request in 1.3110582828521729s
Received healthy response to inference request in 1.2812986373901367s
Received healthy response to inference request in 1.2441277503967285s
5 requests
0 failed requests
5th percentile: 1.2515619277954102
10th percentile: 1.2589961051940919
20th percentile: 1.273864459991455
30th percentile: 1.287250566482544
40th percentile: 1.2991544246673583
50th percentile: 1.3110582828521729
60th percentile: 1.3174874782562256
70th percentile: 1.3239166736602783
80th percentile: 1.49652533531189
90th percentile: 1.8353134632110597
95th percentile: 2.0047075271606443
99th percentile: 2.1402227783203123
mean time: 1.4675435066223144
Pipeline stage StressChecker completed in 7.94s
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-8b_2768_v1 status is now deployed due to DeploymentManager action
hastagaras-esekembrew-8b_2768_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-esekembrew-8b_2768_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-esekembrew-8b-2768-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.10s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-esekembrew-8b-2768-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-8b-2768-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-8b-2768-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-8b-2768-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-8b-2768-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-esekembrew-8b-2768-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-8b-2768-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-8b-2768-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-8b-2768-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-8b-2768-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-8b-2768-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-8b-2768-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.72s
hastagaras-esekembrew-8b_2768_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics