developer_uid: PawanOsman
submission_id: pawankrd-cosmosrp-llama31_v7
model_name: cosmosrp-llama31-test
model_group: PawanKrd/cosmosrp-llama3
status: torndown
timestamp: 2024-07-27T18:49:00+00:00
num_battles: 8260
num_wins: 4332
celo_rating: 1212.73
family_friendly_score: 0.0
submission_type: basic
model_repo: PawanKrd/cosmosrp-llama31
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cosmosrp-llama31-test
is_internal_developer: False
language_model: PawanKrd/cosmosrp-llama31
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-27
win_ratio: 0.524455205811138
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<', '>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 128}
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: {'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 pawankrd-cosmosrp-llama31-v7-mkmlizer
Waiting for job on pawankrd-cosmosrp-llama31-v7-mkmlizer to finish
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
pawankrd-cosmosrp-llama31-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ Version: 0.9.7 ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ║ ║
pawankrd-cosmosrp-llama31-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-llama31-v7-mkmlizer: Downloaded to shared memory in 20.438s
pawankrd-cosmosrp-llama31-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmper5mxea4, device:0
pawankrd-cosmosrp-llama31-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-llama31-v7-mkmlizer: quantized model in 26.558s
pawankrd-cosmosrp-llama31-v7-mkmlizer: Processed model PawanKrd/cosmosrp-llama31 in 46.996s
pawankrd-cosmosrp-llama31-v7-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-llama31-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-llama31-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v7
pawankrd-cosmosrp-llama31-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v7/config.json
pawankrd-cosmosrp-llama31-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v7/special_tokens_map.json
pawankrd-cosmosrp-llama31-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v7/tokenizer_config.json
pawankrd-cosmosrp-llama31-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v7/tokenizer.json
pawankrd-cosmosrp-llama31-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-llama31-v7/flywheel_model.0.safetensors
pawankrd-cosmosrp-llama31-v7-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-llama31-v7-mkmlizer: warnings.warn(
pawankrd-cosmosrp-llama31-v7-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.
pawankrd-cosmosrp-llama31-v7-mkmlizer: warnings.warn(
pawankrd-cosmosrp-llama31-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-llama31-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-llama31-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v7_reward
pawankrd-cosmosrp-llama31-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v7_reward/config.json
pawankrd-cosmosrp-llama31-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v7_reward/tokenizer_config.json
pawankrd-cosmosrp-llama31-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v7_reward/special_tokens_map.json
pawankrd-cosmosrp-llama31-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v7_reward/merges.txt
pawankrd-cosmosrp-llama31-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v7_reward/vocab.json
pawankrd-cosmosrp-llama31-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v7_reward/tokenizer.json
pawankrd-cosmosrp-llama31-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-llama31-v7_reward/reward.tensors
Job pawankrd-cosmosrp-llama31-v7-mkmlizer completed after 84.76s with status: succeeded
Stopping job with name pawankrd-cosmosrp-llama31-v7-mkmlizer
Pipeline stage MKMLizer completed in 85.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-llama31-v7
Waiting for inference service pawankrd-cosmosrp-llama31-v7 to be ready
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Inference service pawankrd-cosmosrp-llama31-v7 ready after 90.8355553150177s
Pipeline stage ISVCDeployer completed in 92.63s
Running pipeline stage StressChecker
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Received healthy response to inference request in 2.067003011703491s
Received healthy response to inference request in 1.3965239524841309s
Received healthy response to inference request in 1.348865270614624s
Received healthy response to inference request in 1.316467523574829s
Received healthy response to inference request in 1.29194974899292s
5 requests
0 failed requests
5th percentile: 1.2968533039093018
10th percentile: 1.3017568588256836
20th percentile: 1.3115639686584473
30th percentile: 1.3229470729827881
40th percentile: 1.335906171798706
50th percentile: 1.348865270614624
60th percentile: 1.3679287433624268
70th percentile: 1.3869922161102295
80th percentile: 1.530619764328003
90th percentile: 1.7988113880157472
95th percentile: 1.932907199859619
99th percentile: 2.0401838493347166
mean time: 1.484161901473999
Pipeline stage StressChecker completed in 8.13s
pawankrd-cosmosrp-llama31_v7 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp-llama31_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of pawankrd-cosmosrp-llama31_v7
Running pipeline stage ISVCDeleter
Checking if service pawankrd-cosmosrp-llama31-v7 is running
Tearing down inference service pawankrd-cosmosrp-llama31-v7
Service pawankrd-cosmosrp-llama31-v7 has been torndown
Pipeline stage ISVCDeleter completed in 4.06s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-llama31-v7/config.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-llama31-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-llama31-v7_reward/config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-llama31-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.44s
pawankrd-cosmosrp-llama31_v7 status is now torndown due to DeploymentManager action