submission_id: thetsar1209-llama3-carp-v0-4_v1
developer_uid: TheTsar1209
status: inactive
model_repo: TheTsar1209/llama3-carp-v0.4
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': ['\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: {'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: 2024-05-08T23:14:10+00:00
model_name: thetsar1209-llama3-carp-v0-4_v1
model_eval_status: success
double_thumbs_up: 235
thumbs_up: 373
thumbs_down: 226
num_battles: 16923
num_wins: 8438
celo_rating: 1175.95
entertaining: 6.72
stay_in_character: 8.21
user_preference: 6.96
safety_score: 0.88
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-v0-4_v1
double_thumbs_up_ratio: 0.28177458033573144
feedback_count: 834
ineligible_reason: None
language_model: TheTsar1209/llama3-carp-v0.4
model_score: 7.296666666666667
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.447242206235012
thumbs_down_ratio: 0.2709832134292566
thumbs_up_ratio: 0.7290167865707434
us_pacific_date: 2024-05-08
win_ratio: 0.49861135732435147
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carp-v0-4-v1-mkmlizer
Waiting for job on thetsar1209-llama3-carp-v0-4-v1-mkmlizer to finish
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║     _____            __           __                                ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║       /___/                                                         ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║  belonging to:                                                      ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║  Chai Research Corp.                                                ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ║                                                                     ║
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carp-v0-4-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-v0-4-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: Downloaded to shared memory in 28.617s
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:02, 77.15it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 80.43it/s]
Loading 0:  99%|█████████▊| 287/291 [00:08<00:00, 27.26it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: quantized model in 19.991s
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: Processed model TheTsar1209/llama3-carp-v0.4 in 49.698s
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v1
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v1/tokenizer_config.json
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v1/config.json
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v1/special_tokens_map.json
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v1/tokenizer.json
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v1/flywheel_model.0.safetensors
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carp-v0-4-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-v0-4-v1-mkmlizer:   warnings.warn(
thetsar1209-llama3-carp-v0-4-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-v0-4-v1-mkmlizer:   warnings.warn(
thetsar1209-llama3-carp-v0-4-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-v0-4-v1-mkmlizer:   warnings.warn(
thetsar1209-llama3-carp-v0-4-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-v0-4-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v1_reward
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v1_reward/config.json
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v1_reward/special_tokens_map.json
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v1_reward/tokenizer_config.json
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v1_reward/merges.txt
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v1_reward/vocab.json
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v1_reward/tokenizer.json
thetsar1209-llama3-carp-v0-4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v1_reward/reward.tensors
Job thetsar1209-llama3-carp-v0-4-v1-mkmlizer completed after 72.87s with status: succeeded
Stopping job with name thetsar1209-llama3-carp-v0-4-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.81s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carp-v0-4-v1
Waiting for inference service thetsar1209-llama3-carp-v0-4-v1 to be ready
Inference service thetsar1209-llama3-carp-v0-4-v1 ready after 30.177469491958618s
Pipeline stage ISVCDeployer completed in 37.36s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.019052505493164s
Received healthy response to inference request in 1.225672960281372s
Received healthy response to inference request in 1.231574296951294s
Received healthy response to inference request in 1.269779920578003s
Received healthy response to inference request in 1.2365100383758545s
5 requests
0 failed requests
5th percentile: 1.2268532276153565
10th percentile: 1.2280334949493408
20th percentile: 1.2303940296173095
30th percentile: 1.2325614452362061
40th percentile: 1.2345357418060303
50th percentile: 1.2365100383758545
60th percentile: 1.2498179912567138
70th percentile: 1.2631259441375733
80th percentile: 1.4196344375610352
90th percentile: 1.7193434715270997
95th percentile: 1.8691979885101317
99th percentile: 1.9890816020965576
mean time: 1.3965179443359375
Pipeline stage StressChecker completed in 7.67s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
thetsar1209-llama3-carp-v0-4_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
thetsar1209-llama3-carp-v0-4_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics