developer_uid: shiroe40
submission_id: cycy233-llm2-0_v3
model_name: role
model_group: cycy233/llm2.0
status: torndown
timestamp: 2024-05-07T16:07:30+00:00
num_battles: 24074
num_wins: 10927
celo_rating: 1133.06
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/llm2.0
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 6738415616.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: role
is_internal_developer: False
language_model: cycy233/llm2.0
model_size: 7B
ranking_group: single
us_pacific_date: 2024-05-07
win_ratio: 0.45389216582204867
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, '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': "{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: {'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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-llm2-0-v3-mkmlizer
Waiting for job on cycy233-llm2-0-v3-mkmlizer to finish
cycy233-llm2-0-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-llm2-0-v3-mkmlizer: ║ _____ __ __ ║
cycy233-llm2-0-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-llm2-0-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-llm2-0-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-llm2-0-v3-mkmlizer: ║ /___/ ║
cycy233-llm2-0-v3-mkmlizer: ║ ║
cycy233-llm2-0-v3-mkmlizer: ║ Version: 0.8.10 ║
cycy233-llm2-0-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-llm2-0-v3-mkmlizer: ║ ║
cycy233-llm2-0-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-llm2-0-v3-mkmlizer: ║ belonging to: ║
cycy233-llm2-0-v3-mkmlizer: ║ ║
cycy233-llm2-0-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-llm2-0-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-llm2-0-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-llm2-0-v3-mkmlizer: ║ ║
cycy233-llm2-0-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-llm2-0-v3-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.
cycy233-llm2-0-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-llm2-0-v3-mkmlizer: Downloaded to shared memory in 24.453s
cycy233-llm2-0-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-llm2-0-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-llm2-0-v3-mkmlizer: quantized model in 14.504s
cycy233-llm2-0-v3-mkmlizer: Processed model cycy233/llm2.0 in 41.094s
cycy233-llm2-0-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-llm2-0-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-llm2-0-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-llm2-0-v3
cycy233-llm2-0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-llm2-0-v3/tokenizer_config.json
cycy233-llm2-0-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-llm2-0-v3/config.json
cycy233-llm2-0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-llm2-0-v3/tokenizer.model
cycy233-llm2-0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-llm2-0-v3/tokenizer.json
cycy233-llm2-0-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-llm2-0-v3/special_tokens_map.json
cycy233-llm2-0-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-llm2-0-v3/flywheel_model.0.safetensors
cycy233-llm2-0-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-llm2-0-v3-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.
cycy233-llm2-0-v3-mkmlizer: warnings.warn(
cycy233-llm2-0-v3-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.
cycy233-llm2-0-v3-mkmlizer: warnings.warn(
cycy233-llm2-0-v3-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.
cycy233-llm2-0-v3-mkmlizer: warnings.warn(
cycy233-llm2-0-v3-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()
cycy233-llm2-0-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-llm2-0-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-llm2-0-v3-mkmlizer: Saving duration: 0.409s
cycy233-llm2-0-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 14.953s
cycy233-llm2-0-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-llm2-0-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-llm2-0-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-llm2-0-v3_reward
cycy233-llm2-0-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-llm2-0-v3_reward/tokenizer_config.json
cycy233-llm2-0-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-llm2-0-v3_reward/special_tokens_map.json
cycy233-llm2-0-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-llm2-0-v3_reward/config.json
cycy233-llm2-0-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-llm2-0-v3_reward/merges.txt
cycy233-llm2-0-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-llm2-0-v3_reward/vocab.json
cycy233-llm2-0-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-llm2-0-v3_reward/tokenizer.json
cycy233-llm2-0-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-llm2-0-v3_reward/reward.tensors
Job cycy233-llm2-0-v3-mkmlizer completed after 359.51s with status: succeeded
Stopping job with name cycy233-llm2-0-v3-mkmlizer
Pipeline stage MKMLizer completed in 364.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-llm2-0-v3
Waiting for inference service cycy233-llm2-0-v3 to be ready
Inference service cycy233-llm2-0-v3 ready after 30.227062225341797s
Pipeline stage ISVCDeployer completed in 38.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.142054796218872s
Received healthy response to inference request in 1.180234432220459s
Received healthy response to inference request in 0.8905549049377441s
Received healthy response to inference request in 1.1577339172363281s
Received healthy response to inference request in 1.1504855155944824s
5 requests
0 failed requests
5th percentile: 0.9425410270690918
10th percentile: 0.9945271492004395
20th percentile: 1.0984993934631349
30th percentile: 1.1519351959228517
40th percentile: 1.1548345565795899
50th percentile: 1.1577339172363281
60th percentile: 1.1667341232299804
70th percentile: 1.1757343292236329
80th percentile: 1.3725985050201417
90th percentile: 1.7573266506195069
95th percentile: 1.9496907234191894
99th percentile: 2.1035819816589356
mean time: 1.304212713241577
Pipeline stage StressChecker completed in 7.48s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
cycy233-llm2-0_v3 status is now deployed due to DeploymentManager action
cycy233-llm2-0_v3 status is now inactive due to auto deactivation removed underperforming models
Deleting key chaoticneutrals-poppy-po-8745-v1/tokenizer.json from bucket guanaco-mkml-models
admin requested tearing down of cycy233-llm2-0_v3
Running pipeline stage ISVCDeleter
Deleting key chaoticneutrals-poppy-po-8745-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Checking if service cycy233-llm2-0-v3 is running
Deleting key chaoticneutrals-poppy-po-8745-v1_reward/config.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-8745-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-8745-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-8745-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-8745-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-8745-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-8745-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.72s
chaoticneutrals-poppy-po_8745_v1 status is now torndown due to DeploymentManager action
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Tearing down inference service cycy233-llm2-0-v3
Toredown service cycy233-llm2-0-v3
Pipeline stage ISVCDeleter completed in 4.19s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-llm2-0-v3/config.json from bucket guanaco-mkml-models
Deleting key cycy233-llm2-0-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-llm2-0-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-llm2-0-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-llm2-0-v3/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-llm2-0-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-llm2-0-v3_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-llm2-0-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-llm2-0-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-llm2-0-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-llm2-0-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-llm2-0-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-llm2-0-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.71s
cycy233-llm2-0_v3 status is now torndown due to DeploymentManager action