developer_uid: TheTsar1209
submission_id: thetsar1209-llama3-carp-v0-2_v3
model_name: thetsar1209-llama3-carp-v0-2_v2
model_group: TheTsar1209/llama3-carp-
status: torndown
timestamp: 2024-04-21T17:58:41+00:00
num_battles: 5392
num_wins: 3010
celo_rating: 1188.02
family_friendly_score: 0.0
submission_type: basic
model_repo: TheTsar1209/llama3-carp-v0.2
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: thetsar1209-llama3-carp-v0-2_v2
is_internal_developer: False
language_model: TheTsar1209/llama3-carp-v0.2
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-21
win_ratio: 0.5582344213649851
generation_params: {'temperature': 1.0, 'top_p': 1.0, '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|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': False}
model_eval_status: success
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carp-v0-2-v3-mkmlizer
Waiting for job on thetsar1209-llama3-carp-v0-2-v3-mkmlizer to finish
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ _____ __ __ ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ /___/ ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ Version: 0.8.10 ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ The license key for the current software has been verified as ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ belonging to: ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ Chai Research Corp. ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carp-v0-2-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.
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: Downloaded to shared memory in 20.441s
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 74.61it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 80.40it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 28.12it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: quantized model in 19.904s
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: Processed model TheTsar1209/llama3-carp-v0.2 in 41.860s
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-2-v3
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-2-v3/tokenizer_config.json
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-2-v3/config.json
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-2-v3/special_tokens_map.json
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-2-v3/tokenizer.json
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-2-v3/flywheel_model.0.safetensors
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carp-v0-2-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.
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-2-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.
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-2-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()
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: return self.fget.__get__(instance, owner)()
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: Saving duration: 0.289s
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.510s
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v3_reward
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v3_reward/config.json
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v3_reward/special_tokens_map.json
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v3_reward/tokenizer_config.json
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v3_reward/vocab.json
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v3_reward/merges.txt
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v3_reward/tokenizer.json
thetsar1209-llama3-carp-v0-2-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v3_reward/reward.tensors
Job thetsar1209-llama3-carp-v0-2-v3-mkmlizer completed after 75.0s with status: succeeded
Stopping job with name thetsar1209-llama3-carp-v0-2-v3-mkmlizer
Pipeline stage MKMLizer completed in 79.77s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carp-v0-2-v3
Waiting for inference service thetsar1209-llama3-carp-v0-2-v3 to be ready
Inference service thetsar1209-llama3-carp-v0-2-v3 ready after 40.27385449409485s
Pipeline stage ISVCDeployer completed in 49.00s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.171536922454834s
Received healthy response to inference request in 1.3201258182525635s
Received healthy response to inference request in 1.2977321147918701s
Received healthy response to inference request in 1.698789358139038s
Received healthy response to inference request in 1.3082878589630127s
5 requests
0 failed requests
5th percentile: 1.2998432636260986
10th percentile: 1.301954412460327
20th percentile: 1.3061767101287842
30th percentile: 1.310655450820923
40th percentile: 1.3153906345367432
50th percentile: 1.3201258182525635
60th percentile: 1.4715912342071533
70th percentile: 1.6230566501617432
80th percentile: 1.7933388710021974
90th percentile: 1.9824378967285157
95th percentile: 2.0769874095916747
99th percentile: 2.152627019882202
mean time: 1.5592944145202636
Pipeline stage StressChecker completed in 8.56s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.07s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.09s
thetsar1209-llama3-carp-v0-2_v3 status is now deployed due to DeploymentManager action
thetsar1209-llama3-carp-v0-2_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of thetsar1209-llama3-carp-v0-2_v3
Running pipeline stage ISVCDeleter
Checking if service thetsar1209-llama3-carp-v0-2-v3 is running
Tearing down inference service thetsar1209-llama3-carp-v0-2-v3
Toredown service thetsar1209-llama3-carp-v0-2-v3
Pipeline stage ISVCDeleter completed in 3.63s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carp-v0-2-v3/config.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-v0-2-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-v0-2-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-v0-2-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-v0-2-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carp-v0-2-v3_reward/config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-2-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-2-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-2-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-2-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-2-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-2-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.79s
thetsar1209-llama3-carp-v0-2_v3 status is now torndown due to DeploymentManager action