submission_id: jellywibble-chateaulafit_7738_v1
developer_uid: Jellywibble
status: inactive
model_repo: Jellywibble/ChateauLafite8BRawQLORA
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|>{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}
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: 2024-05-22T06:45:14+00:00
model_name: jellywibble-chateaulafit_7738_v1
model_eval_status: success
model_group: Jellywibble/ChateauLafit
num_battles: 5575
num_wins: 3069
celo_rating: 1208.16
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: jellywibble-chateaulafit_7738_v1
ineligible_reason: propriety_total_count < 5000
language_model: Jellywibble/ChateauLafite8BRawQLORA
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-21
win_ratio: 0.5504932735426009
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jellywibble-chateaulafit-7738-v1-mkmlizer
Waiting for job on jellywibble-chateaulafit-7738-v1-mkmlizer to finish
jellywibble-chateaulafit-7738-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ _____ __ __ ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ /___/ ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ Version: 0.8.14 ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ https://mk1.ai ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ The license key for the current software has been verified as ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ belonging to: ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ Chai Research Corp. ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ║ ║
jellywibble-chateaulafit-7738-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-chateaulafit-7738-v1-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.
jellywibble-chateaulafit-7738-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
generated new fontManager
blend_ragum_2024-05-22 status is now deployed due to DeploymentManager action
jellywibble-chateaulafit-7738-v1-mkmlizer: Downloaded to shared memory in 55.388s
jellywibble-chateaulafit-7738-v1-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-chateaulafit-7738-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-chateaulafit-7738-v1-mkmlizer: Processed model Jellywibble/ChateauLafite8BRawQLORA in 80.930s
jellywibble-chateaulafit-7738-v1-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-chateaulafit-7738-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-chateaulafit-7738-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v1
jellywibble-chateaulafit-7738-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v1/config.json
jellywibble-chateaulafit-7738-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v1/tokenizer_config.json
jellywibble-chateaulafit-7738-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v1/tokenizer.json
jellywibble-chateaulafit-7738-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v1/special_tokens_map.json
jellywibble-chateaulafit-7738-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v1/flywheel_model.0.safetensors
jellywibble-chateaulafit-7738-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
jellywibble-chateaulafit-7738-v1-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.
jellywibble-chateaulafit-7738-v1-mkmlizer: warnings.warn(
jellywibble-chateaulafit-7738-v1-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.
jellywibble-chateaulafit-7738-v1-mkmlizer: warnings.warn(
jellywibble-chateaulafit-7738-v1-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.
jellywibble-chateaulafit-7738-v1-mkmlizer: warnings.warn(
jellywibble-chateaulafit-7738-v1-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()
jellywibble-chateaulafit-7738-v1-mkmlizer: return self.fget.__get__(instance, owner)()
jellywibble-chateaulafit-7738-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-chateaulafit-7738-v1-mkmlizer: Saving duration: 0.264s
jellywibble-chateaulafit-7738-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.705s
jellywibble-chateaulafit-7738-v1-mkmlizer: creating bucket guanaco-reward-models
jellywibble-chateaulafit-7738-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-chateaulafit-7738-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v1_reward
jellywibble-chateaulafit-7738-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v1_reward/tokenizer_config.json
jellywibble-chateaulafit-7738-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v1_reward/config.json
jellywibble-chateaulafit-7738-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v1_reward/special_tokens_map.json
jellywibble-chateaulafit-7738-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v1_reward/vocab.json
jellywibble-chateaulafit-7738-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v1_reward/merges.txt
jellywibble-chateaulafit-7738-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v1_reward/tokenizer.json
jellywibble-chateaulafit-7738-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v1_reward/reward.tensors
Job jellywibble-chateaulafit-7738-v1-mkmlizer completed after 103.57s with status: succeeded
Stopping job with name jellywibble-chateaulafit-7738-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.60s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-chateaulafit-7738-v1
Waiting for inference service jellywibble-chateaulafit-7738-v1 to be ready
Inference service jellywibble-chateaulafit-7738-v1 ready after 30.18750238418579s
Pipeline stage ISVCDeployer completed in 35.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.095085620880127s
Received healthy response to inference request in 1.2502539157867432s
Received healthy response to inference request in 1.2508549690246582s
Received healthy response to inference request in 1.262763261795044s
Received healthy response to inference request in 1.2636947631835938s
5 requests
0 failed requests
5th percentile: 1.2503741264343262
10th percentile: 1.2504943370819093
20th percentile: 1.2507347583770752
30th percentile: 1.2532366275787354
40th percentile: 1.2579999446868897
50th percentile: 1.262763261795044
60th percentile: 1.2631358623504638
70th percentile: 1.2635084629058837
80th percentile: 1.4299729347229007
90th percentile: 1.7625292778015138
95th percentile: 1.92880744934082
99th percentile: 2.0618299865722656
mean time: 1.4245305061340332
Pipeline stage StressChecker completed in 7.70s
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
jellywibble-chateaulafit_7738_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
jellywibble-chateaulafit_7738_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics