submission_id: hastagaras-aelah-8b-llam_5487_v3
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Aelah-8B-Llama3-TEST
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 0.98, 'min_p': 0.05, 'top_k': 80, '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: 2024-06-12T01:20:22+00:00
model_name: propriety-test
model_eval_status: success
model_group: Hastagaras/Aelah-8B-Llam
num_battles: 23891
num_wins: 12544
celo_rating: 1193.99
propriety_score: 0.7016608570842732
propriety_total_count: 9754.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: propriety-test
ineligible_reason: None
language_model: Hastagaras/Aelah-8B-Llama3-TEST
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-11
win_ratio: 0.5250512745385292
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-aelah-8b-llam-5487-v3-mkmlizer
Waiting for job on hastagaras-aelah-8b-llam-5487-v3-mkmlizer to finish
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ /___/ ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ belonging to: ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ║ ║
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-aelah-8b-llam-5487-v3-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-aelah-8b-llam-5487-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: Downloaded to shared memory in 40.686s
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 126.26it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 147.62it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 154.12it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 157.26it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 80.49it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 97.94it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 112.72it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 124.78it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 134.85it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 139.40it/s] Loading 0: 65%|██████▍ | 189/291 [00:01<00:01, 78.83it/s] Loading 0: 70%|███████ | 204/291 [00:01<00:00, 90.65it/s] Loading 0: 76%|███████▌ | 221/291 [00:02<00:00, 104.43it/s] Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 117.91it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 128.69it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 137.07it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 10.17it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: quantized model in 19.879s
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: Processed model Hastagaras/Aelah-8B-Llama3-TEST in 61.562s
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v3
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v3/config.json
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v3/special_tokens_map.json
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v3/tokenizer_config.json
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v3/tokenizer.json
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-aelah-8b-llam-5487-v3-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-aelah-8b-llam-5487-v3-mkmlizer: warnings.warn(
hastagaras-aelah-8b-llam-5487-v3-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-aelah-8b-llam-5487-v3-mkmlizer: warnings.warn(
hastagaras-aelah-8b-llam-5487-v3-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-aelah-8b-llam-5487-v3-mkmlizer: warnings.warn(
hastagaras-aelah-8b-llam-5487-v3-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-aelah-8b-llam-5487-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: Saving duration: 0.263s
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.048s
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v3_reward
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v3_reward/config.json
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v3_reward/special_tokens_map.json
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v3_reward/tokenizer_config.json
hastagaras-aelah-8b-llam-5487-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v3_reward/reward.tensors
Job hastagaras-aelah-8b-llam-5487-v3-mkmlizer completed after 94.45s with status: succeeded
Stopping job with name hastagaras-aelah-8b-llam-5487-v3-mkmlizer
Pipeline stage MKMLizer completed in 95.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-aelah-8b-llam-5487-v3
Waiting for inference service hastagaras-aelah-8b-llam-5487-v3 to be ready
Inference service hastagaras-aelah-8b-llam-5487-v3 ready after 50.41582536697388s
Pipeline stage ISVCDeployer completed in 56.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1499412059783936s
Received healthy response to inference request in 1.3479406833648682s
Received healthy response to inference request in 1.3003599643707275s
Received healthy response to inference request in 1.2965731620788574s
Received healthy response to inference request in 1.2714710235595703s
5 requests
0 failed requests
5th percentile: 1.2764914512634278
10th percentile: 1.2815118789672852
20th percentile: 1.291552734375
30th percentile: 1.2973305225372314
40th percentile: 1.2988452434539794
50th percentile: 1.3003599643707275
60th percentile: 1.3193922519683838
70th percentile: 1.3384245395660401
80th percentile: 1.5083407878875734
90th percentile: 1.8291409969329835
95th percentile: 1.9895411014556883
99th percentile: 2.1178611850738527
mean time: 1.4732572078704833
Pipeline stage StressChecker completed in 7.97s
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-aelah-8b-llam_5487_v3 status is now deployed due to DeploymentManager action
hastagaras-aelah-8b-llam_5487_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics