submission_id: cgato-l3-thespice-8b-dpo_6189_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v2.3-e3.2.1
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: 2024-05-02T00:43:53+00:00
model_name: cgato-l3-thespice-8b-dpo_6189_v1
model_eval_status: success
double_thumbs_up: 165
thumbs_up: 284
thumbs_down: 135
num_battles: 12938
num_wins: 7159
celo_rating: 1217.29
entertaining: 7.24
stay_in_character: 8.27
user_preference: 7.32
safety_score: 0.79
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_6189_v1
double_thumbs_up_ratio: 0.2825342465753425
feedback_count: 584
ineligible_reason: None
language_model: cgato/L3-TheSpice-8b-DPO-v2.3-e3.2.1
model_score: 7.609999999999999
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4863013698630137
thumbs_down_ratio: 0.23116438356164384
thumbs_up_ratio: 0.7688356164383562
us_pacific_date: 2024-05-01
win_ratio: 0.5533312722213635
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer to finish
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-6189-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.
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: Downloaded to shared memory in 35.545s
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 80.53it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 127.77it/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-6189-v1-mkmlizer: quantized model in 18.932s
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v2.3-e3.2.1 in 55.531s
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6189-v1
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6189-v1/tokenizer.json
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6189-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-6189-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.
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6189-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.
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6189-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.
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6189-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()
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: Saving duration: 0.309s
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.571s
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6189-v1_reward
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6189-v1_reward/config.json
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6189-v1_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6189-v1_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6189-v1_reward/merges.txt
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6189-v1_reward/vocab.json
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6189-v1_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6189-v1_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer completed after 83.59s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-6189-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.11s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-6189-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-6189-v1 to be ready
Inference service cgato-l3-thespice-8b-dpo-6189-v1 ready after 40.25979495048523s
Pipeline stage ISVCDeployer completed in 47.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2818381786346436s
Received healthy response to inference request in 1.2853596210479736s
Received healthy response to inference request in 1.2917242050170898s
Received healthy response to inference request in 1.2818267345428467s
Received healthy response to inference request in 1.2851171493530273s
5 requests
0 failed requests
5th percentile: 1.2824848175048829
10th percentile: 1.283142900466919
20th percentile: 1.2844590663909912
30th percentile: 1.2851656436920167
40th percentile: 1.2852626323699952
50th percentile: 1.2853596210479736
60th percentile: 1.2879054546356201
70th percentile: 1.2904512882232666
80th percentile: 1.4897469997406008
90th percentile: 1.8857925891876222
95th percentile: 2.0838153839111326
99th percentile: 2.2422336196899413
mean time: 1.4851731777191162
Pipeline stage StressChecker completed in 8.06s
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_6189_v1 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_6189_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics