submission_id: hastagaras-aelah-8b-llam_5487_v4
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': 1.0, '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': "<|begin_of_text|><|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: 2024-06-12T01:20:54+00:00
model_name: propriety-test
model_eval_status: success
model_group: Hastagaras/Aelah-8B-Llam
num_battles: 23923
num_wins: 12510
celo_rating: 1192.9
propriety_score: 0.6999495204442201
propriety_total_count: 9905.0
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: 0.5229277264557121
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-aelah-8b-llam-5487-v4-mkmlizer
Waiting for job on hastagaras-aelah-8b-llam-5487-v4-mkmlizer to finish
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ _____ __ __ ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ /___/ ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ https://mk1.ai ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ belonging to: ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ Chai Research Corp. ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ║ ║
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-aelah-8b-llam-5487-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-aelah-8b-llam-5487-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:01, 193.83it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:01, 188.30it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 213.17it/s] Loading 0: 30%|███ | 88/291 [00:00<00:01, 105.25it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 130.97it/s] Loading 0: 45%|████▌ | 131/291 [00:00<00:01, 145.74it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 170.71it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 185.80it/s] Loading 0: 69%|██████▉ | 201/291 [00:01<00:00, 115.75it/s] Loading 0: 76%|███████▌ | 221/291 [00:01<00:00, 129.90it/s] Loading 0: 85%|████████▍ | 246/291 [00:01<00:00, 154.22it/s] Loading 0: 91%|█████████▏| 266/291 [00:01<00:00, 163.24it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 13.92it/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-v4-mkmlizer: quantized model in 16.984s
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: Processed model Hastagaras/Aelah-8B-Llama3-TEST in 35.803s
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v4
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v4/tokenizer_config.json
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v4/config.json
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v4/special_tokens_map.json
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v4/tokenizer.json
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v4/flywheel_model.0.safetensors
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-aelah-8b-llam-5487-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-aelah-8b-llam-5487-v4-mkmlizer: warnings.warn(
hastagaras-aelah-8b-llam-5487-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-aelah-8b-llam-5487-v4-mkmlizer: warnings.warn(
hastagaras-aelah-8b-llam-5487-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-aelah-8b-llam-5487-v4-mkmlizer: warnings.warn(
hastagaras-aelah-8b-llam-5487-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-aelah-8b-llam-5487-v4-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: Saving duration: 0.232s
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 2.713s
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v4_reward
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v4_reward/config.json
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v4_reward/special_tokens_map.json
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v4_reward/tokenizer_config.json
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v4_reward/vocab.json
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v4_reward/merges.txt
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v4_reward/tokenizer.json
hastagaras-aelah-8b-llam-5487-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v4_reward/reward.tensors
Job hastagaras-aelah-8b-llam-5487-v4-mkmlizer completed after 62.75s with status: succeeded
Stopping job with name hastagaras-aelah-8b-llam-5487-v4-mkmlizer
Pipeline stage MKMLizer completed in 67.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-aelah-8b-llam-5487-v4
Waiting for inference service hastagaras-aelah-8b-llam-5487-v4 to be ready
Inference service hastagaras-aelah-8b-llam-5487-v4 ready after 40.25033903121948s
Pipeline stage ISVCDeployer completed in 47.62s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.150601387023926s
Received healthy response to inference request in 1.344810962677002s
Received healthy response to inference request in 1.3084359169006348s
Received healthy response to inference request in 1.282848596572876s
Received healthy response to inference request in 1.3662869930267334s
5 requests
0 failed requests
5th percentile: 1.2879660606384278
10th percentile: 1.2930835247039796
20th percentile: 1.303318452835083
30th percentile: 1.3157109260559081
40th percentile: 1.330260944366455
50th percentile: 1.344810962677002
60th percentile: 1.3534013748168945
70th percentile: 1.361991786956787
80th percentile: 1.523149871826172
90th percentile: 1.836875629425049
95th percentile: 1.9937385082244872
99th percentile: 2.119228811264038
mean time: 1.4905967712402344
Pipeline stage StressChecker completed in 8.05s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-aelah-8b-llam_5487_v4 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-aelah-8b-llam_5487_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics