submission_id: hastagaras-llama3-8b-claoas_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/llama3-8b-CLaOaS
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.05, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name} in this vivid and engaging roleplay.\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': 'Message Example:\n{bot_name}: {prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{bot_name}: {prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-05-05T11:45:22+00:00
model_name: hastagaras-llama3-8b-claoas_v1
model_eval_status: success
double_thumbs_up: 209
thumbs_up: 296
thumbs_down: 213
num_battles: 16993
num_wins: 8307
celo_rating: 1161.31
entertaining: 6.68
stay_in_character: 8.33
user_preference: 6.7
safety_score: 0.86
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-llama3-8b-claoas_v1
double_thumbs_up_ratio: 0.29108635097493035
feedback_count: 718
ineligible_reason: None
language_model: Hastagaras/llama3-8b-CLaOaS
model_score: 7.236666666666667
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.41225626740947074
thumbs_down_ratio: 0.2966573816155989
thumbs_up_ratio: 0.7033426183844012
us_pacific_date: 2024-05-05
win_ratio: 0.48884834932030835
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-8b-claoas-v2-mkmlizer
Waiting for job on hastagaras-llama3-8b-claoas-v2-mkmlizer to finish
Stopping job with name hastagaras-llama3-8b-claoas-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-llama3-8b-claoas-v2-mkmlizer
Waiting for job on hastagaras-llama3-8b-claoas-v2-mkmlizer to finish
hastagaras-llama3-8b-claoas-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ /___/ ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ belonging to: ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ║ ║
hastagaras-llama3-8b-claoas-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-8b-claoas-v2-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.
hastagaras-llama3-8b-claoas-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-8b-claoas-v2-mkmlizer: Downloaded to shared memory in 14.841s
hastagaras-llama3-8b-claoas-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-8b-claoas-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-8b-claoas-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 66.94it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 72.94it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 27.16it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-8b-claoas-v2-mkmlizer: quantized model in 20.656s
hastagaras-llama3-8b-claoas-v2-mkmlizer: Processed model Hastagaras/llama3-8b-CLaOaS in 36.786s
hastagaras-llama3-8b-claoas-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-8b-claoas-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-8b-claoas-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-8b-claoas-v2
hastagaras-llama3-8b-claoas-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-claoas-v2/config.json
hastagaras-llama3-8b-claoas-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-8b-claoas-v2/special_tokens_map.json
hastagaras-llama3-8b-claoas-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-claoas-v2/tokenizer_config.json
hastagaras-llama3-8b-claoas-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-8b-claoas-v2/tokenizer.json
hastagaras-llama3-8b-claoas-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-8b-claoas-v2/flywheel_model.0.safetensors
hastagaras-llama3-8b-claoas-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-8b-claoas-v2-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.
hastagaras-llama3-8b-claoas-v2-mkmlizer: warnings.warn(
hastagaras-llama3-8b-claoas-v2-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.
hastagaras-llama3-8b-claoas-v2-mkmlizer: warnings.warn(
hastagaras-llama3-8b-claoas-v2-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.
hastagaras-llama3-8b-claoas-v2-mkmlizer: warnings.warn(
hastagaras-llama3-8b-claoas-v2-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()
hastagaras-llama3-8b-claoas-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama3-8b-claoas-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-8b-claoas-v2-mkmlizer: Saving duration: 0.282s
hastagaras-llama3-8b-claoas-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 19.157s
hastagaras-llama3-8b-claoas-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-8b-claoas-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-8b-claoas-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v2_reward
hastagaras-llama3-8b-claoas-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v2_reward/special_tokens_map.json
hastagaras-llama3-8b-claoas-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v2_reward/tokenizer_config.json
hastagaras-llama3-8b-claoas-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v2_reward/merges.txt
hastagaras-llama3-8b-claoas-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v2_reward/vocab.json
hastagaras-llama3-8b-claoas-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v2_reward/config.json
hastagaras-llama3-8b-claoas-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v2_reward/tokenizer.json
hastagaras-llama3-8b-claoas-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v2_reward/reward.tensors
Job hastagaras-llama3-8b-claoas-v2-mkmlizer completed after 83.07s with status: succeeded
Stopping job with name hastagaras-llama3-8b-claoas-v2-mkmlizer
Pipeline stage MKMLizer completed in 86.36s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-8b-claoas-v2
Waiting for inference service hastagaras-llama3-8b-claoas-v2 to be ready
Inference service hastagaras-llama3-8b-claoas-v2 ready after 40.36141061782837s
Pipeline stage ISVCDeployer completed in 47.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9575674533843994s
Received healthy response to inference request in 1.2259488105773926s
Received healthy response to inference request in 1.2381939888000488s
Received healthy response to inference request in 1.2388014793395996s
Received healthy response to inference request in 1.3095431327819824s
5 requests
0 failed requests
5th percentile: 1.2283978462219238
10th percentile: 1.230846881866455
20th percentile: 1.2357449531555176
30th percentile: 1.238315486907959
40th percentile: 1.2385584831237793
50th percentile: 1.2388014793395996
60th percentile: 1.2670981407165527
70th percentile: 1.2953948020935058
80th percentile: 1.4391479969024659
90th percentile: 1.6983577251434328
95th percentile: 1.827962589263916
99th percentile: 1.9316464805603026
mean time: 1.3940109729766845
Pipeline stage StressChecker completed in 7.59s
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
hastagaras-llama3-8b-claoas_v2 status is now deployed due to DeploymentManager action
hastagaras-llama3-8b-claoas_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics