developer_uid: Locutusque
submission_id: locutusque-apollo-0-3-ll_7860_v1
model_name: locutusque-apollo-0-3-ll_7860_v1
model_group: Locutusque/Apollo-0.3-Ll
status: torndown
timestamp: 2024-07-24T17:27:53+00:00
num_battles: 15961
num_wins: 7559
celo_rating: 1181.48
family_friendly_score: 0.0
submission_type: basic
model_repo: Locutusque/Apollo-0.3-Llama-3-8B
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 6
max_input_tokens: 1024
max_output_tokens: 64
display_name: locutusque-apollo-0-3-ll_7860_v1
is_internal_developer: False
language_model: Locutusque/Apollo-0.3-Llama-3-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-24
win_ratio: 0.473591880208007
generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.05, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|im_end|>', '<|end_of_text|>'], 'max_input_tokens': 1024, 'best_of': 6, 'max_output_tokens': 64, 'reward_max_token_input': 1024}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name locutusque-apollo-0-3-ll-7860-v1-mkmlizer
Waiting for job on locutusque-apollo-0-3-ll-7860-v1-mkmlizer to finish
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ _____ __ __ ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ /___/ ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ Version: 0.9.6 ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ https://mk1.ai ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ The license key for the current software has been verified as ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ belonging to: ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ Chai Research Corp. ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ║ ║
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: Downloaded to shared memory in 43.071s
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp99xlpjzg, device:0
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: creating bucket guanaco-mkml-models
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/locutusque-apollo-0-3-ll-7860-v1
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/locutusque-apollo-0-3-ll-7860-v1/config.json
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/locutusque-apollo-0-3-ll-7860-v1/special_tokens_map.json
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/locutusque-apollo-0-3-ll-7860-v1/tokenizer_config.json
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/locutusque-apollo-0-3-ll-7860-v1/tokenizer.json
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/locutusque-apollo-0-3-ll-7860-v1/flywheel_model.0.safetensors
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: warnings.warn(
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: warnings.warn(
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: warnings.warn(
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: Saving duration: 0.331s
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.790s
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: creating bucket guanaco-reward-models
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/locutusque-apollo-0-3-ll-7860-v1_reward
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/locutusque-apollo-0-3-ll-7860-v1_reward/special_tokens_map.json
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/locutusque-apollo-0-3-ll-7860-v1_reward/config.json
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/locutusque-apollo-0-3-ll-7860-v1_reward/tokenizer_config.json
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/locutusque-apollo-0-3-ll-7860-v1_reward/merges.txt
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/locutusque-apollo-0-3-ll-7860-v1_reward/vocab.json
locutusque-apollo-0-3-ll-7860-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/locutusque-apollo-0-3-ll-7860-v1_reward/tokenizer.json
Job locutusque-apollo-0-3-ll-7860-v1-mkmlizer completed after 108.11s with status: succeeded
Stopping job with name locutusque-apollo-0-3-ll-7860-v1-mkmlizer
Pipeline stage MKMLizer completed in 109.15s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service locutusque-apollo-0-3-ll-7860-v1
Waiting for inference service locutusque-apollo-0-3-ll-7860-v1 to be ready
Failed to get response for submission blend_dunet_2024-07-19: ('http://undi95-meta-llama-3-70b-6209-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
Inference service locutusque-apollo-0-3-ll-7860-v1 ready after 50.615549087524414s
Pipeline stage ISVCDeployer completed in 52.76s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1008553504943848s
Received healthy response to inference request in 1.2646484375s
Received healthy response to inference request in 1.2587168216705322s
Received healthy response to inference request in 1.2594797611236572s
Received healthy response to inference request in 1.2173233032226562s
5 requests
0 failed requests
5th percentile: 1.2256020069122315
10th percentile: 1.2338807106018066
20th percentile: 1.250438117980957
30th percentile: 1.2588694095611572
40th percentile: 1.2591745853424072
50th percentile: 1.2594797611236572
60th percentile: 1.2615472316741942
70th percentile: 1.2636147022247315
80th percentile: 1.4318898200988772
90th percentile: 1.766372585296631
95th percentile: 1.9336139678955075
99th percentile: 2.0674070739746093
mean time: 1.4202047348022462
Pipeline stage StressChecker completed in 7.79s
locutusque-apollo-0-3-ll_7860_v1 status is now deployed due to DeploymentManager action
locutusque-apollo-0-3-ll_7860_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of locutusque-apollo-0-3-ll_7860_v1
Running pipeline stage ISVCDeleter
Checking if service locutusque-apollo-0-3-ll-7860-v1 is running
Tearing down inference service locutusque-apollo-0-3-ll-7860-v1
Service locutusque-apollo-0-3-ll-7860-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.67s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key locutusque-apollo-0-3-ll-7860-v1/config.json from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-3-ll-7860-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-3-ll-7860-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-3-ll-7860-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key locutusque-apollo-0-3-ll-7860-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key locutusque-apollo-0-3-ll-7860-v1_reward/config.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-3-ll-7860-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-3-ll-7860-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-3-ll-7860-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-3-ll-7860-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-3-ll-7860-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key locutusque-apollo-0-3-ll-7860-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.10s
locutusque-apollo-0-3-ll_7860_v1 status is now torndown due to DeploymentManager action