submission_id: cgato-l3-thespice-8b-dpo_7976_v2
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e19.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'You:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s Persona: {memory}\n", 'prompt_template': '***\n{prompt}\n***<|im_end|>\n', 'bot_template': '<|im_start|>{bot_name}\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>{bot_name}\n{bot_name}:', 'truncate_by_message': True}
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': True}
timestamp: 2024-06-07T02:03:28+00:00
model_name: cgato-l3-thespice-8b-dpo_7976_v2
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 11176
num_wins: 5904
celo_rating: 1210.68
safety_score: 0.94
propriety_score: 0.6430412371134021
propriety_total_count: 776.0
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-dpo_7976_v2
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e19.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-06
win_ratio: 0.5282748747315676
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer to finish
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-7976-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-7976-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: Downloaded to shared memory in 62.468s
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 58.20it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 72.89it/s] Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 103.43it/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-7976-v2-mkmlizer: quantized model in 24.398s
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e19.2 in 89.410s
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7976-v2
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7976-v2/config.json
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7976-v2/tokenizer_config.json
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7976-v2/tokenizer.json
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7976-v2/special_tokens_map.json
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7976-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-7976-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-7976-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-7976-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-7976-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-7976-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.
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-7976-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-7976-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: Saving duration: 1.107s
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 18.245s
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v2_reward
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v2_reward/merges.txt
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v2_reward/config.json
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v2_reward/vocab.json
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v2_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7976-v2_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer completed after 124.25s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-7976-v2-mkmlizer
Pipeline stage MKMLizer completed in 127.38s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-7976-v2
Waiting for inference service cgato-l3-thespice-8b-dpo-7976-v2 to be ready
Inference service cgato-l3-thespice-8b-dpo-7976-v2 ready after 40.280553340911865s
Pipeline stage ISVCDeployer completed in 47.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1900758743286133s
Received healthy response to inference request in 1.3068056106567383s
Received healthy response to inference request in 1.3189599514007568s
Received healthy response to inference request in 1.3070075511932373s
Received healthy response to inference request in 1.2988524436950684s
5 requests
0 failed requests
5th percentile: 1.3004430770874023
10th percentile: 1.3020337104797364
20th percentile: 1.3052149772644044
30th percentile: 1.3068459987640382
40th percentile: 1.3069267749786377
50th percentile: 1.3070075511932373
60th percentile: 1.311788511276245
70th percentile: 1.3165694713592528
80th percentile: 1.4931831359863283
90th percentile: 1.8416295051574707
95th percentile: 2.015852689743042
99th percentile: 2.155231237411499
mean time: 1.484340286254883
Pipeline stage StressChecker completed in 8.10s
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_7976_v2 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_7976_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics