submission_id: cgato-l3-thespice-8b-v3-3_v10
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-v3.3
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: 2024-05-08T10:49:36+00:00
model_name: cgato-l3-thespice-8b-v3-3_v10
model_eval_status: success
double_thumbs_up: 131
thumbs_up: 149
thumbs_down: 61
num_battles: 11180
num_wins: 5973
celo_rating: 1199.75
entertaining: 7.1
stay_in_character: 8.71
user_preference: 7.58
safety_score: 0.94
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030277632.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-l3-thespice-8b-v3-3_v10
double_thumbs_up_ratio: 0.3841642228739003
feedback_count: 341
ineligible_reason: None
language_model: cgato/L3-TheSpice-8b-v3.3
model_score: 7.796666666666667
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.436950146627566
thumbs_down_ratio: 0.17888563049853373
thumbs_up_ratio: 0.8211143695014663
us_pacific_date: 2024-05-08
win_ratio: 0.534257602862254
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-v3-3-v10-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v3-3-v10-mkmlizer to finish
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ║ ║
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-v3-3-v10-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-v3-3-v10-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: Downloaded to shared memory in 17.403s
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 120.55it/s] Loading 0: 90%|████████▉ | 261/291 [00:02<00:00, 131.93it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 28.14it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: quantized model in 18.382s
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: Processed model cgato/L3-TheSpice-8b-v3.3 in 36.853s
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-3-v10
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-3-v10/special_tokens_map.json
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-3-v10/config.json
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-3-v10/tokenizer_config.json
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-3-v10/tokenizer.json
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-3-v10/flywheel_model.0.safetensors
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-v3-3-v10-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-v3-3-v10-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v3-3-v10-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-v3-3-v10-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v3-3-v10-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-v3-3-v10-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: Saving duration: 0.226s
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.013s
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v10_reward
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v10_reward/config.json
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v10_reward/special_tokens_map.json
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v10_reward/vocab.json
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v10_reward/tokenizer_config.json
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v10_reward/tokenizer.json
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v10_reward/merges.txt
cgato-l3-thespice-8b-v3-3-v10-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v10_reward/reward.tensors
Job cgato-l3-thespice-8b-v3-3-v10-mkmlizer completed after 64.14s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-v3-3-v10-mkmlizer
Pipeline stage MKMLizer completed in 68.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-v3-3-v10
Waiting for inference service cgato-l3-thespice-8b-v3-3-v10 to be ready
Inference service cgato-l3-thespice-8b-v3-3-v10 ready after 40.24135684967041s
Pipeline stage ISVCDeployer completed in 48.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2285754680633545s
Received healthy response to inference request in 1.3093969821929932s
Received healthy response to inference request in 1.2616615295410156s
Received healthy response to inference request in 1.2632100582122803s
Received healthy response to inference request in 1.2524781227111816s
5 requests
0 failed requests
5th percentile: 1.2543148040771483
10th percentile: 1.2561514854431153
20th percentile: 1.259824848175049
30th percentile: 1.2619712352752686
40th percentile: 1.2625906467437744
50th percentile: 1.2632100582122803
60th percentile: 1.2816848278045654
70th percentile: 1.3001595973968505
80th percentile: 1.4932326793670656
90th percentile: 1.86090407371521
95th percentile: 2.044739770889282
99th percentile: 2.19180832862854
mean time: 1.463064432144165
Pipeline stage StressChecker completed in 8.54s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.05s
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-v3-3_v10 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-v3-3_v10 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics