submission_id: thetsar1209-llama3-carp-v0-2_v4
developer_uid: TheTsar1209
status: inactive
model_repo: TheTsar1209/llama3-carp-v0.2
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|>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}
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: 2024-05-09T00:51:51+00:00
model_name: thetsar1209-llama3-carp-v0-2_v2
model_eval_status: success
double_thumbs_up: 135
thumbs_up: 213
thumbs_down: 71
num_battles: 8887
num_wins: 4543
celo_rating: 1189.15
entertaining: 7.28
stay_in_character: 8.48
user_preference: 7.24
safety_score: 0.91
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-v0-2_v2
double_thumbs_up_ratio: 0.3221957040572792
feedback_count: 419
ineligible_reason: None
language_model: TheTsar1209/llama3-carp-v0.2
model_score: 7.666666666666667
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.5083532219570406
thumbs_down_ratio: 0.16945107398568018
thumbs_up_ratio: 0.8305489260143198
us_pacific_date: 2024-05-08
win_ratio: 0.5111961291774502
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carp-v0-2-v4-mkmlizer
Waiting for job on thetsar1209-llama3-carp-v0-2-v4-mkmlizer to finish
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ _____ __ __ ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ /___/ ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ Version: 0.8.10 ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ The license key for the current software has been verified as ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ belonging to: ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ Chai Research Corp. ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carp-v0-2-v4-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-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: Downloaded to shared memory in 29.872s
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:02, 92.73it/s] Loading 0: 65%|██████▍ | 189/291 [00:02<00:01, 93.77it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 29.36it/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-v4-mkmlizer: quantized model in 19.607s
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: Processed model TheTsar1209/llama3-carp-v0.2 in 50.469s
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-2-v4
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-2-v4/config.json
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-2-v4/tokenizer_config.json
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-2-v4/special_tokens_map.json
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-2-v4/tokenizer.json
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-2-v4/flywheel_model.0.safetensors
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carp-v0-2-v4-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-v4-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-2-v4-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-v4-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-2-v4-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-v0-2-v4-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: Saving duration: 0.258s
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.929s
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v4_reward
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v4_reward/special_tokens_map.json
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v4_reward/config.json
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v4_reward/vocab.json
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v4_reward/tokenizer_config.json
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v4_reward/merges.txt
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v4_reward/tokenizer.json
thetsar1209-llama3-carp-v0-2-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-2-v4_reward/reward.tensors
Job thetsar1209-llama3-carp-v0-2-v4-mkmlizer completed after 73.52s with status: succeeded
Stopping job with name thetsar1209-llama3-carp-v0-2-v4-mkmlizer
Pipeline stage MKMLizer completed in 76.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carp-v0-2-v4
Waiting for inference service thetsar1209-llama3-carp-v0-2-v4 to be ready
Inference service thetsar1209-llama3-carp-v0-2-v4 ready after 30.17380952835083s
Pipeline stage ISVCDeployer completed in 37.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.348557233810425s
Received healthy response to inference request in 1.2790000438690186s
Received healthy response to inference request in 1.2764956951141357s
Received healthy response to inference request in 1.3089053630828857s
Received healthy response to inference request in 1.2910616397857666s
5 requests
0 failed requests
5th percentile: 1.2769965648651123
10th percentile: 1.2774974346160888
20th percentile: 1.278499174118042
30th percentile: 1.2814123630523682
40th percentile: 1.2862370014190674
50th percentile: 1.2910616397857666
60th percentile: 1.2981991291046142
70th percentile: 1.3053366184234618
80th percentile: 1.5168357372283938
90th percentile: 1.9326964855194093
95th percentile: 2.1406268596649167
99th percentile: 2.306971158981323
mean time: 1.5008039951324463
Pipeline stage StressChecker completed in 8.18s
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 0.06s
M-Eval Dataset for topic stay_in_character is loaded
thetsar1209-llama3-carp-v0-2_v4 status is now deployed due to DeploymentManager action
thetsar1209-llama3-carp-v0-2_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics