submission_id: hastagaras-esekmbrew-0-2_v4
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/esekmbrew-0.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.95, '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: 2024-05-17T13:49:42+00:00
model_name: huehe3
model_eval_status: success
model_group: Hastagaras/esekmbrew-0.2
num_battles: 14062
num_wins: 7274
celo_rating: 1182.49
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: huehe3
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/esekmbrew-0.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-17
win_ratio: 0.5172806144218461
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-esekmbrew-0-2-v4-mkmlizer
Waiting for job on hastagaras-esekmbrew-0-2-v4-mkmlizer to finish
hastagaras-esekmbrew-0-2-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ _____ __ __ ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ /___/ ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ https://mk1.ai ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ belonging to: ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ Chai Research Corp. ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ║ ║
hastagaras-esekmbrew-0-2-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekmbrew-0-2-v4-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-esekmbrew-0-2-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-esekmbrew-0-2-v4-mkmlizer: Downloaded to shared memory in 17.459s
hastagaras-esekmbrew-0-2-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekmbrew-0-2-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekmbrew-0-2-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 135.38it/s] Loading 0: 12%|█▏ | 35/291 [00:00<00:01, 177.70it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:01, 188.03it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:01, 184.62it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 77.93it/s] Loading 0: 40%|████ | 117/291 [00:01<00:01, 102.17it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 122.66it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 137.08it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 155.36it/s] Loading 0: 68%|██████▊ | 199/291 [00:01<00:01, 87.49it/s] Loading 0: 75%|███████▌ | 219/291 [00:01<00:00, 105.33it/s] Loading 0: 82%|████████▏ | 238/291 [00:01<00:00, 120.10it/s] Loading 0: 89%|████████▉ | 260/291 [00:02<00:00, 140.05it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 155.35it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekmbrew-0-2-v4-mkmlizer: quantized model in 18.159s
hastagaras-esekmbrew-0-2-v4-mkmlizer: Processed model Hastagaras/esekmbrew-0.2 in 36.744s
hastagaras-esekmbrew-0-2-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekmbrew-0-2-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekmbrew-0-2-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekmbrew-0-2-v4
hastagaras-esekmbrew-0-2-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekmbrew-0-2-v4/config.json
hastagaras-esekmbrew-0-2-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekmbrew-0-2-v4/special_tokens_map.json
hastagaras-esekmbrew-0-2-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekmbrew-0-2-v4/tokenizer_config.json
hastagaras-esekmbrew-0-2-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekmbrew-0-2-v4/tokenizer.json
hastagaras-esekmbrew-0-2-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-esekmbrew-0-2-v4/flywheel_model.0.safetensors
hastagaras-esekmbrew-0-2-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekmbrew-0-2-v4-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-esekmbrew-0-2-v4-mkmlizer: warnings.warn(
hastagaras-esekmbrew-0-2-v4-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-esekmbrew-0-2-v4-mkmlizer: warnings.warn(
hastagaras-esekmbrew-0-2-v4-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-esekmbrew-0-2-v4-mkmlizer: warnings.warn(
hastagaras-esekmbrew-0-2-v4-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-esekmbrew-0-2-v4-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-esekmbrew-0-2-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekmbrew-0-2-v4-mkmlizer: Saving duration: 0.270s
hastagaras-esekmbrew-0-2-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.036s
hastagaras-esekmbrew-0-2-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-esekmbrew-0-2-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekmbrew-0-2-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v4_reward
hastagaras-esekmbrew-0-2-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v4_reward/config.json
hastagaras-esekmbrew-0-2-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v4_reward/tokenizer_config.json
hastagaras-esekmbrew-0-2-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v4_reward/vocab.json
hastagaras-esekmbrew-0-2-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v4_reward/merges.txt
hastagaras-esekmbrew-0-2-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v4_reward/special_tokens_map.json
hastagaras-esekmbrew-0-2-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v4_reward/tokenizer.json
hastagaras-esekmbrew-0-2-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v4_reward/reward.tensors
Job hastagaras-esekmbrew-0-2-v4-mkmlizer completed after 63.45s with status: succeeded
Stopping job with name hastagaras-esekmbrew-0-2-v4-mkmlizer
Pipeline stage MKMLizer completed in 66.73s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekmbrew-0-2-v4
Waiting for inference service hastagaras-esekmbrew-0-2-v4 to be ready
Inference service hastagaras-esekmbrew-0-2-v4 ready after 30.348416566848755s
Pipeline stage ISVCDeployer completed in 37.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0713560581207275s
Received healthy response to inference request in 1.25006103515625s
Received healthy response to inference request in 1.2578768730163574s
Received healthy response to inference request in 1.2285809516906738s
Received healthy response to inference request in 1.2164807319641113s
5 requests
0 failed requests
5th percentile: 1.218900775909424
10th percentile: 1.2213208198547363
20th percentile: 1.2261609077453612
30th percentile: 1.232876968383789
40th percentile: 1.2414690017700196
50th percentile: 1.25006103515625
60th percentile: 1.253187370300293
70th percentile: 1.2563137054443358
80th percentile: 1.4205727100372316
90th percentile: 1.7459643840789796
95th percentile: 1.9086602210998533
99th percentile: 2.0388168907165527
mean time: 1.404871129989624
Pipeline stage StressChecker completed in 7.66s
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-esekmbrew-0-2_v4 status is now deployed due to DeploymentManager action
hastagaras-esekmbrew-0-2_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics