submission_id: cgato-l3-thespice-8b-dpo_4448_v2
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v2.3-e7.1
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': 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: 2024-05-06T22:47:05+00:00
model_name: cgato-l3-thespice-8b-dpo_4448_v2
model_eval_status: success
double_thumbs_up: 344
thumbs_up: 461
thumbs_down: 259
num_battles: 22020
num_wins: 12587
celo_rating: 1228.9
entertaining: 6.62
stay_in_character: 8.15
user_preference: 6.38
safety_score: 0.71
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-l3-thespice-8b-dpo_4448_v2
double_thumbs_up_ratio: 0.3233082706766917
feedback_count: 1064
ineligible_reason: None
language_model: cgato/L3-TheSpice-8b-DPO-v2.3-e7.1
model_score: 7.05
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4332706766917293
thumbs_down_ratio: 0.24342105263157895
thumbs_up_ratio: 0.756578947368421
us_pacific_date: 2024-05-06
win_ratio: 0.5716167120799274
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer to finish
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-4448-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.
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: Downloaded to shared memory in 13.232s
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:00, 104.91it/s] Loading 0: 100%|██████████| 291/291 [00:06<00:00, 39.32it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: quantized model in 17.314s
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v2.3-e7.1 in 31.611s
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4448-v2
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4448-v2/config.json
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4448-v2/special_tokens_map.json
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4448-v2/tokenizer_config.json
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4448-v2/tokenizer.json
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-4448-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-4448-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.
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-4448-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.
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-4448-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()
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: Saving duration: 0.233s
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.617s
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4448-v2_reward
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4448-v2_reward/config.json
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4448-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4448-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4448-v2_reward/merges.txt
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4448-v2_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4448-v2_reward/vocab.json
cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-4448-v2_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer completed after 185.77s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-4448-v2-mkmlizer
Pipeline stage MKMLizer completed in 188.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-4448-v2
Waiting for inference service cgato-l3-thespice-8b-dpo-4448-v2 to be ready
Inference service cgato-l3-thespice-8b-dpo-4448-v2 ready after 30.18783402442932s
Pipeline stage ISVCDeployer completed in 37.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3817906379699707s
Received healthy response to inference request in 1.2976124286651611s
Received healthy response to inference request in 1.2869572639465332s
Received healthy response to inference request in 1.2766385078430176s
Received healthy response to inference request in 1.3017158508300781s
5 requests
0 failed requests
5th percentile: 1.2787022590637207
10th percentile: 1.2807660102844238
20th percentile: 1.28489351272583
30th percentile: 1.2890882968902588
40th percentile: 1.2933503627777099
50th percentile: 1.2976124286651611
60th percentile: 1.299253797531128
70th percentile: 1.3008951663970947
80th percentile: 1.5177308082580567
90th percentile: 1.9497607231140137
95th percentile: 2.165775680541992
99th percentile: 2.338587646484375
mean time: 1.5089429378509522
Pipeline stage StressChecker completed in 8.15s
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
cgato-l3-thespice-8b-dpo_4448_v2 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_4448_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics