submission_id: hastagaras-esekembrew-0-3_v5
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Esekembrew-0.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 200, '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: 2024-05-17T18:03:31+00:00
model_name: mwehehehehe
model_eval_status: success
model_group: Hastagaras/Esekembrew-0.
num_battles: 27363
num_wins: 15061
celo_rating: 1204.7
safety_score: 0.96
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: mwehehehehe
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Esekembrew-0.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-17
win_ratio: 0.5504147936995213
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-esekembrew-0-3-v5-mkmlizer
Waiting for job on hastagaras-esekembrew-0-3-v5-mkmlizer to finish
hastagaras-esekembrew-0-3-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ _____ __ __ ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ /___/ ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ https://mk1.ai ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ belonging to: ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ Chai Research Corp. ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekembrew-0-3-v5-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-0-3-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-esekembrew-0-3-v5-mkmlizer: Downloaded to shared memory in 12.177s
hastagaras-esekembrew-0-3-v5-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekembrew-0-3-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekembrew-0-3-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:01, 207.84it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:01, 197.41it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 206.68it/s] Loading 0: 30%|██▉ | 87/291 [00:00<00:02, 94.81it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 121.38it/s] Loading 0: 44%|████▍ | 129/291 [00:00<00:01, 133.84it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 139.10it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:00, 134.70it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:00, 131.02it/s] Loading 0: 67%|██████▋ | 196/291 [00:01<00:01, 81.18it/s] Loading 0: 75%|███████▌ | 219/291 [00:01<00:00, 104.97it/s] Loading 0: 81%|████████▏ | 237/291 [00:01<00:00, 116.40it/s] Loading 0: 87%|████████▋ | 252/291 [00:02<00:00, 117.98it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 138.34it/s] Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 11.67it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekembrew-0-3-v5-mkmlizer: quantized model in 17.816s
hastagaras-esekembrew-0-3-v5-mkmlizer: Processed model Hastagaras/Esekembrew-0.3 in 31.027s
hastagaras-esekembrew-0-3-v5-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekembrew-0-3-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekembrew-0-3-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v5
hastagaras-esekembrew-0-3-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v5/config.json
hastagaras-esekembrew-0-3-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v5/special_tokens_map.json
hastagaras-esekembrew-0-3-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v5/tokenizer_config.json
hastagaras-esekembrew-0-3-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v5/tokenizer.json
hastagaras-esekembrew-0-3-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v5/flywheel_model.0.safetensors
hastagaras-esekembrew-0-3-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekembrew-0-3-v5-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-0-3-v5-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-v5-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-0-3-v5-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-v5-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-0-3-v5-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-esekembrew-0-3-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekembrew-0-3-v5-mkmlizer: Saving duration: 0.246s
hastagaras-esekembrew-0-3-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.359s
hastagaras-esekembrew-0-3-v5-mkmlizer: creating bucket guanaco-reward-models
hastagaras-esekembrew-0-3-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekembrew-0-3-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v5_reward
hastagaras-esekembrew-0-3-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v5_reward/config.json
hastagaras-esekembrew-0-3-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v5_reward/tokenizer_config.json
hastagaras-esekembrew-0-3-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v5_reward/special_tokens_map.json
hastagaras-esekembrew-0-3-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v5_reward/merges.txt
hastagaras-esekembrew-0-3-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v5_reward/vocab.json
hastagaras-esekembrew-0-3-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v5_reward/tokenizer.json
hastagaras-esekembrew-0-3-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v5_reward/reward.tensors
Job hastagaras-esekembrew-0-3-v5-mkmlizer completed after 52.56s with status: succeeded
Stopping job with name hastagaras-esekembrew-0-3-v5-mkmlizer
Pipeline stage MKMLizer completed in 57.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekembrew-0-3-v5
Waiting for inference service hastagaras-esekembrew-0-3-v5 to be ready
Inference service hastagaras-esekembrew-0-3-v5 ready after 30.215052843093872s
Pipeline stage ISVCDeployer completed in 37.74s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3387722969055176s
Received healthy response to inference request in 1.3546595573425293s
Received healthy response to inference request in 1.3458099365234375s
Received healthy response to inference request in 1.316481351852417s
Received healthy response to inference request in 1.375143051147461s
5 requests
0 failed requests
5th percentile: 1.322347068786621
10th percentile: 1.3282127857208252
20th percentile: 1.3399442195892335
30th percentile: 1.3475798606872558
40th percentile: 1.3511197090148925
50th percentile: 1.3546595573425293
60th percentile: 1.3628529548645019
70th percentile: 1.3710463523864747
80th percentile: 1.5678689002990724
90th percentile: 1.953320598602295
95th percentile: 2.146046447753906
99th percentile: 2.3002271270751953
mean time: 1.5461732387542724
Pipeline stage StressChecker completed in 8.51s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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 0.06s
hastagaras-esekembrew-0-3_v5 status is now deployed due to DeploymentManager action
hastagaras-esekembrew-0-3_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics