submission_id: hastagaras-esekembrew-0-3_v6
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Esekembrew-0.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, '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': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-05-18T00:40:38+00:00
model_name: mwehehew
model_eval_status: success
model_group: Hastagaras/Esekembrew-0.
num_battles: 15797
num_wins: 8807
celo_rating: 1205.73
safety_score: 0.95
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: mwehehew
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: 0.5575109197948978
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-esekembrew-0-3-v6-mkmlizer
Waiting for job on hastagaras-esekembrew-0-3-v6-mkmlizer to finish
hastagaras-esekembrew-0-3-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ _____ __ __ ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ /___/ ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ https://mk1.ai ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ belonging to: ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ Chai Research Corp. ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ║ ║
hastagaras-esekembrew-0-3-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekembrew-0-3-v6-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-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-esekembrew-0-3-v6-mkmlizer: Downloaded to shared memory in 15.290s
hastagaras-esekembrew-0-3-v6-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekembrew-0-3-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekembrew-0-3-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 125.39it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 146.01it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 154.51it/s] Loading 0: 22%|██▏ | 64/291 [00:00<00:01, 153.02it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 147.27it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 70.98it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 88.10it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 104.03it/s] Loading 0: 49%|████▉ | 143/291 [00:01<00:01, 110.97it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 117.26it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 136.54it/s] Loading 0: 67%|██████▋ | 195/291 [00:01<00:01, 81.61it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:00, 94.88it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 108.59it/s] Loading 0: 84%|████████▎ | 243/291 [00:02<00:00, 117.03it/s] Loading 0: 89%|████████▊ | 258/291 [00:02<00:00, 121.93it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 131.01it/s] Loading 0: 99%|█████████▉| 289/291 [00:08<00:00, 8.34it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekembrew-0-3-v6-mkmlizer: quantized model in 20.459s
hastagaras-esekembrew-0-3-v6-mkmlizer: Processed model Hastagaras/Esekembrew-0.3 in 36.745s
hastagaras-esekembrew-0-3-v6-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekembrew-0-3-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekembrew-0-3-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v6
hastagaras-esekembrew-0-3-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v6/config.json
hastagaras-esekembrew-0-3-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v6/special_tokens_map.json
hastagaras-esekembrew-0-3-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v6/tokenizer_config.json
hastagaras-esekembrew-0-3-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v6/tokenizer.json
hastagaras-esekembrew-0-3-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-esekembrew-0-3-v6/flywheel_model.0.safetensors
hastagaras-esekembrew-0-3-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekembrew-0-3-v6-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-v6-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-v6-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-v6-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-v6-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-0-3-v6-mkmlizer: warnings.warn(
hastagaras-esekembrew-0-3-v6-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-v6-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-esekembrew-0-3-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekembrew-0-3-v6-mkmlizer: Saving duration: 0.237s
hastagaras-esekembrew-0-3-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.599s
hastagaras-esekembrew-0-3-v6-mkmlizer: creating bucket guanaco-reward-models
hastagaras-esekembrew-0-3-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekembrew-0-3-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v6_reward
hastagaras-esekembrew-0-3-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v6_reward/special_tokens_map.json
hastagaras-esekembrew-0-3-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v6_reward/vocab.json
hastagaras-esekembrew-0-3-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v6_reward/config.json
hastagaras-esekembrew-0-3-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v6_reward/merges.txt
hastagaras-esekembrew-0-3-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v6_reward/tokenizer_config.json
hastagaras-esekembrew-0-3-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v6_reward/tokenizer.json
hastagaras-esekembrew-0-3-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-esekembrew-0-3-v6_reward/reward.tensors
Job hastagaras-esekembrew-0-3-v6-mkmlizer completed after 64.71s with status: succeeded
Stopping job with name hastagaras-esekembrew-0-3-v6-mkmlizer
Pipeline stage MKMLizer completed in 67.43s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekembrew-0-3-v6
Waiting for inference service hastagaras-esekembrew-0-3-v6 to be ready
Inference service hastagaras-esekembrew-0-3-v6 ready after 40.28158926963806s
Pipeline stage ISVCDeployer completed in 47.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1324729919433594s
Received healthy response to inference request in 1.3672690391540527s
Received healthy response to inference request in 1.5320408344268799s
Received healthy response to inference request in 1.3046908378601074s
Received healthy response to inference request in 1.2819600105285645s
5 requests
0 failed requests
5th percentile: 1.286506175994873
10th percentile: 1.2910523414611816
20th percentile: 1.3001446723937988
30th percentile: 1.3172064781188966
40th percentile: 1.3422377586364747
50th percentile: 1.3672690391540527
60th percentile: 1.4331777572631836
70th percentile: 1.4990864753723143
80th percentile: 1.6521272659301758
90th percentile: 1.8923001289367676
95th percentile: 2.0123865604400635
99th percentile: 2.1084557056427
mean time: 1.5236867427825929
Pipeline stage StressChecker completed in 8.35s
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 0.06s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-esekembrew-0-3_v6 status is now deployed due to DeploymentManager action
hastagaras-esekembrew-0-3_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics