submission_id: thetsar1209-llama3-carp-_3767_v1
developer_uid: TheTsar1209
status: torndown
model_repo: TheTsar1209/llama3-carp-v0.4.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\nYou are {bot_name}\nDescription : {memory}\n', 'prompt_template': 'Example conversation:\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistantshort\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistantshort\n', 'truncate_by_message': False}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot: ', 'truncate_by_message': False}
timestamp: 2024-05-12T23:39:56+00:00
model_name: thetsar1209-llama3-carp-_3767_v1
model_eval_status: success
model_group: TheTsar1209/llama3-carp-
num_battles: 20443
num_wins: 10896
celo_rating: 1191.09
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: thetsar1209-llama3-carp-_3767_v1
ineligible_reason: propriety_total_count < 800
language_model: TheTsar1209/llama3-carp-v0.4.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-12
win_ratio: 0.5329941789365553
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carp-3767-v1-mkmlizer
Waiting for job on thetsar1209-llama3-carp-3767-v1-mkmlizer to finish
thetsar1209-llama3-carp-3767-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ _____ __ __ ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ /___/ ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ Version: 0.8.10 ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ The license key for the current software has been verified as ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ belonging to: ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ Chai Research Corp. ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ║ ║
thetsar1209-llama3-carp-3767-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carp-3767-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.
thetsar1209-llama3-carp-3767-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
thetsar1209-llama3-carp-3767-v1-mkmlizer: Downloaded to shared memory in 27.268s
thetsar1209-llama3-carp-3767-v1-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carp-3767-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carp-3767-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 31%|███ | 90/291 [00:00<00:02, 90.09it/s] Loading 0: 65%|██████▍ | 189/291 [00:02<00:01, 94.41it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 29.86it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
thetsar1209-llama3-carp-3767-v1-mkmlizer: quantized model in 19.010s
thetsar1209-llama3-carp-3767-v1-mkmlizer: Processed model TheTsar1209/llama3-carp-v0.4.1 in 47.337s
thetsar1209-llama3-carp-3767-v1-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carp-3767-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carp-3767-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carp-3767-v1
thetsar1209-llama3-carp-3767-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-3767-v1/special_tokens_map.json
thetsar1209-llama3-carp-3767-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-3767-v1/config.json
thetsar1209-llama3-carp-3767-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-3767-v1/tokenizer_config.json
thetsar1209-llama3-carp-3767-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-3767-v1/tokenizer.json
thetsar1209-llama3-carp-3767-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carp-3767-v1/flywheel_model.0.safetensors
thetsar1209-llama3-carp-3767-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carp-3767-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.
thetsar1209-llama3-carp-3767-v1-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-3767-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.
thetsar1209-llama3-carp-3767-v1-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-3767-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.
thetsar1209-llama3-carp-3767-v1-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-3767-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()
thetsar1209-llama3-carp-3767-v1-mkmlizer: return self.fget.__get__(instance, owner)()
thetsar1209-llama3-carp-3767-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thetsar1209-llama3-carp-3767-v1-mkmlizer: Saving duration: 0.250s
thetsar1209-llama3-carp-3767-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.791s
thetsar1209-llama3-carp-3767-v1-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carp-3767-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carp-3767-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carp-3767-v1_reward
thetsar1209-llama3-carp-3767-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-3767-v1_reward/tokenizer_config.json
thetsar1209-llama3-carp-3767-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carp-3767-v1_reward/special_tokens_map.json
thetsar1209-llama3-carp-3767-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-3767-v1_reward/config.json
thetsar1209-llama3-carp-3767-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carp-3767-v1_reward/merges.txt
thetsar1209-llama3-carp-3767-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carp-3767-v1_reward/vocab.json
thetsar1209-llama3-carp-3767-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carp-3767-v1_reward/tokenizer.json
thetsar1209-llama3-carp-3767-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thetsar1209-llama3-carp-3767-v1_reward/reward.tensors
Job thetsar1209-llama3-carp-3767-v1-mkmlizer completed after 73.34s with status: succeeded
Stopping job with name thetsar1209-llama3-carp-3767-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carp-3767-v1
Waiting for inference service thetsar1209-llama3-carp-3767-v1 to be ready
Inference service thetsar1209-llama3-carp-3767-v1 ready after 30.20967388153076s
Pipeline stage ISVCDeployer completed in 37.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.073812484741211s
Received healthy response to inference request in 1.2723722457885742s
Received healthy response to inference request in 1.2779877185821533s
Received healthy response to inference request in 1.2861742973327637s
Received healthy response to inference request in 1.2672297954559326s
5 requests
0 failed requests
5th percentile: 1.268258285522461
10th percentile: 1.2692867755889892
20th percentile: 1.271343755722046
30th percentile: 1.27349534034729
40th percentile: 1.2757415294647216
50th percentile: 1.2779877185821533
60th percentile: 1.2812623500823974
70th percentile: 1.2845369815826415
80th percentile: 1.4437019348144533
90th percentile: 1.7587572097778321
95th percentile: 1.9162848472595213
99th percentile: 2.042306957244873
mean time: 1.4355153083801269
Pipeline stage StressChecker completed in 7.72s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
thetsar1209-llama3-carp-_3767_v1 status is now deployed due to DeploymentManager action
thetsar1209-llama3-carp-_3767_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of thetsar1209-llama3-carp-_3767_v1
Running pipeline stage ISVCDeleter
Checking if service thetsar1209-llama3-carp-3767-v1 is running
Tearing down inference service thetsar1209-llama3-carp-3767-v1
Toredown service thetsar1209-llama3-carp-3767-v1
Pipeline stage ISVCDeleter completed in 4.24s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carp-3767-v1/config.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-3767-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-3767-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-3767-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-3767-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carp-3767-v1_reward/config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-3767-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-3767-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-3767-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-3767-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-3767-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-3767-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.16s
thetsar1209-llama3-carp-_3767_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics