submission_id: cgato-l3-thespice-8b-dpo_5027_v3
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e17.2
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|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\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: 2024-06-05T01:57:16+00:00
model_name: cgato-l3-thespice-8b-dpo_5027_v3
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 19375
num_wins: 10141
celo_rating: 1200.49
propriety_score: 0.6568627450980392
propriety_total_count: 612.0
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_5027_v3
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e17.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-04
win_ratio: 0.5234064516129032
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer to finish
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-5027-v3-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-5027-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: Downloaded to shared memory in 14.993s
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 60.08it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 73.06it/s] Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 108.06it/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-5027-v3-mkmlizer: quantized model in 21.246s
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e17.2 in 37.725s
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5027-v3
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5027-v3/special_tokens_map.json
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5027-v3/tokenizer_config.json
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5027-v3/config.json
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5027-v3/tokenizer.json
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5027-v3/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-5027-v3-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-5027-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5027-v3-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-5027-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5027-v3-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-5027-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5027-v3-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-5027-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: Saving duration: 0.263s
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.078s
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v3_reward
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v3_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v3_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v3_reward/vocab.json
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v3_reward/config.json
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v3_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v3_reward/merges.txt
cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v3_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer completed after 63.09s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-5027-v3-mkmlizer
Pipeline stage MKMLizer completed in 68.03s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-5027-v3
Waiting for inference service cgato-l3-thespice-8b-dpo-5027-v3 to be ready
Inference service cgato-l3-thespice-8b-dpo-5027-v3 ready after 60.37244915962219s
Pipeline stage ISVCDeployer completed in 68.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2689292430877686s
Received healthy response to inference request in 1.3080329895019531s
Received healthy response to inference request in 1.3159890174865723s
Received healthy response to inference request in 1.308546543121338s
Received healthy response to inference request in 1.3156018257141113s
5 requests
0 failed requests
5th percentile: 1.30813570022583
10th percentile: 1.308238410949707
20th percentile: 1.308443832397461
30th percentile: 1.3099575996398927
40th percentile: 1.312779712677002
50th percentile: 1.3156018257141113
60th percentile: 1.3157567024230956
70th percentile: 1.3159115791320801
80th percentile: 1.5065770626068118
90th percentile: 1.8877531528472902
95th percentile: 2.078341197967529
99th percentile: 2.2308116340637207
mean time: 1.5034199237823487
Pipeline stage StressChecker completed in 8.11s
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_5027_v3 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_5027_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics