submission_id: maldv-badger-lambda-llam_7421_v2
developer_uid: maldevide
status: inactive
model_repo: maldv/badger-lambda-llama-3-8b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>', 'You:'], '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\nRoleplay. Your name is {bot_name}, and are meeting someone named {user_name}.\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: 2024-06-10T20:17:35+00:00
model_name: maldv-badger-lambda
model_eval_status: success
model_group: maldv/badger-lambda-llam
num_battles: 29891
num_wins: 14540
celo_rating: 1164.95
propriety_score: 0.7239489938234708
propriety_total_count: 10038.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: maldv-badger-lambda
ineligible_reason: None
language_model: maldv/badger-lambda-llama-3-8b
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-10
win_ratio: 0.4864340436920812
Resubmit model
Running pipeline stage MKMLizer
Starting job with name maldv-badger-lambda-llam-7421-v2-mkmlizer
Waiting for job on maldv-badger-lambda-llam-7421-v2-mkmlizer to finish
maldv-badger-lambda-llam-7421-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ _____ __ __ ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ /___/ ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ Version: 0.8.14 ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ https://mk1.ai ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ The license key for the current software has been verified as ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ belonging to: ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ Chai Research Corp. ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ║ ║
maldv-badger-lambda-llam-7421-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
maldv-badger-lambda-llam-7421-v2-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.
maldv-badger-lambda-llam-7421-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
maldv-badger-lambda-llam-7421-v2-mkmlizer: Downloaded to shared memory in 23.530s
maldv-badger-lambda-llam-7421-v2-mkmlizer: quantizing model to /dev/shm/model_cache
maldv-badger-lambda-llam-7421-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
maldv-badger-lambda-llam-7421-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:00<00:15, 18.07it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:02, 111.51it/s] Loading 0: 11%|█▏ | 33/291 [00:00<00:02, 92.24it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:02, 115.99it/s] Loading 0: 22%|██▏ | 63/291 [00:00<00:02, 97.32it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:01, 126.87it/s] Loading 0: 34%|███▍ | 99/291 [00:00<00:01, 107.76it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:01, 110.23it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 121.80it/s] Loading 0: 53%|█████▎ | 153/291 [00:01<00:01, 105.98it/s] Loading 0: 60%|██████ | 175/291 [00:01<00:00, 128.00it/s] Loading 0: 65%|██████▍ | 189/291 [00:01<00:00, 111.18it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 111.48it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 122.40it/s] Loading 0: 84%|████████▎ | 243/291 [00:02<00:00, 106.57it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 127.85it/s] Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 11.65it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
maldv-badger-lambda-llam-7421-v2-mkmlizer: quantized model in 17.153s
maldv-badger-lambda-llam-7421-v2-mkmlizer: Processed model maldv/badger-lambda-llama-3-8b in 41.598s
maldv-badger-lambda-llam-7421-v2-mkmlizer: creating bucket guanaco-mkml-models
maldv-badger-lambda-llam-7421-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
maldv-badger-lambda-llam-7421-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/maldv-badger-lambda-llam-7421-v2
maldv-badger-lambda-llam-7421-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/maldv-badger-lambda-llam-7421-v2/special_tokens_map.json
maldv-badger-lambda-llam-7421-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/maldv-badger-lambda-llam-7421-v2/config.json
maldv-badger-lambda-llam-7421-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/maldv-badger-lambda-llam-7421-v2/tokenizer_config.json
maldv-badger-lambda-llam-7421-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/maldv-badger-lambda-llam-7421-v2/tokenizer.json
maldv-badger-lambda-llam-7421-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/maldv-badger-lambda-llam-7421-v2/flywheel_model.0.safetensors
maldv-badger-lambda-llam-7421-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
maldv-badger-lambda-llam-7421-v2-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.
maldv-badger-lambda-llam-7421-v2-mkmlizer: warnings.warn(
maldv-badger-lambda-llam-7421-v2-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.
maldv-badger-lambda-llam-7421-v2-mkmlizer: warnings.warn(
maldv-badger-lambda-llam-7421-v2-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.
maldv-badger-lambda-llam-7421-v2-mkmlizer: warnings.warn(
maldv-badger-lambda-llam-7421-v2-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()
maldv-badger-lambda-llam-7421-v2-mkmlizer: return self.fget.__get__(instance, owner)()
maldv-badger-lambda-llam-7421-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
maldv-badger-lambda-llam-7421-v2-mkmlizer: Saving duration: 0.218s
maldv-badger-lambda-llam-7421-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.221s
maldv-badger-lambda-llam-7421-v2-mkmlizer: creating bucket guanaco-reward-models
maldv-badger-lambda-llam-7421-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
maldv-badger-lambda-llam-7421-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v2_reward
maldv-badger-lambda-llam-7421-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v2_reward/vocab.json
maldv-badger-lambda-llam-7421-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v2_reward/tokenizer_config.json
maldv-badger-lambda-llam-7421-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v2_reward/special_tokens_map.json
maldv-badger-lambda-llam-7421-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v2_reward/merges.txt
maldv-badger-lambda-llam-7421-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v2_reward/config.json
maldv-badger-lambda-llam-7421-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v2_reward/tokenizer.json
maldv-badger-lambda-llam-7421-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/maldv-badger-lambda-llam-7421-v2_reward/reward.tensors
Job maldv-badger-lambda-llam-7421-v2-mkmlizer completed after 62.92s with status: succeeded
Stopping job with name maldv-badger-lambda-llam-7421-v2-mkmlizer
Pipeline stage MKMLizer completed in 67.32s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service maldv-badger-lambda-llam-7421-v2
Waiting for inference service maldv-badger-lambda-llam-7421-v2 to be ready
Inference service maldv-badger-lambda-llam-7421-v2 ready after 40.322657108306885s
Pipeline stage ISVCDeployer completed in 47.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.186664342880249s
Received healthy response to inference request in 1.3236911296844482s
Received healthy response to inference request in 1.3095049858093262s
Received healthy response to inference request in 1.2512891292572021s
Received healthy response to inference request in 1.3089196681976318s
5 requests
0 failed requests
5th percentile: 1.262815237045288
10th percentile: 1.274341344833374
20th percentile: 1.297393560409546
30th percentile: 1.3090367317199707
40th percentile: 1.3092708587646484
50th percentile: 1.3095049858093262
60th percentile: 1.315179443359375
70th percentile: 1.3208539009094238
80th percentile: 1.4962857723236085
90th percentile: 1.8414750576019288
95th percentile: 2.014069700241089
99th percentile: 2.152145414352417
mean time: 1.4760138511657714
Pipeline stage StressChecker completed in 8.11s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
maldv-badger-lambda-llam_7421_v2 status is now deployed due to DeploymentManager action
maldv-badger-lambda-llam_7421_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics