submission_id: cgato-l3-thespice-8b-dpo_2839_v3
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e8.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 200, '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: 2024-05-23T02:46:09+00:00
model_name: cgato-l3-thespice-8b-dpo_2839_v3
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 6961
num_wins: 3664
celo_rating: 1194.5
safety_score: 0.94
propriety_score: 0.0
propriety_total_count: 0.0
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_2839_v3
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e8.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-22
win_ratio: 0.5263611550064646
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer to finish
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-2839-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-2839-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: Downloaded to shared memory in 22.929s
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 82.22it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 98.16it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 142.52it/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-2839-v3-mkmlizer: quantized model in 18.613s
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e8.1 in 42.573s
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2839-v3
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2839-v3/config.json
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2839-v3/special_tokens_map.json
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2839-v3/tokenizer_config.json
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2839-v3/tokenizer.json
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2839-v3/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-2839-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-2839-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-2839-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-2839-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-2839-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-2839-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-2839-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-2839-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: Saving duration: 0.303s
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.507s
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2839-v3_reward/config.json
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2839-v3_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2839-v3_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2839-v3_reward/merges.txt
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2839-v3_reward/vocab.json
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2839-v3_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2839-v3_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer completed after 73.36s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-2839-v3-mkmlizer
Pipeline stage MKMLizer completed in 74.11s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-2839-v3
Waiting for inference service cgato-l3-thespice-8b-dpo-2839-v3 to be ready
Inference service cgato-l3-thespice-8b-dpo-2839-v3 ready after 30.16268754005432s
Pipeline stage ISVCDeployer completed in 36.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.144279718399048s
Received healthy response to inference request in 1.279179573059082s
Received healthy response to inference request in 1.2942914962768555s
Received healthy response to inference request in 1.2773442268371582s
Received healthy response to inference request in 1.292797565460205s
5 requests
0 failed requests
5th percentile: 1.2777112960815429
10th percentile: 1.2780783653259278
20th percentile: 1.2788125038146974
30th percentile: 1.2819031715393066
40th percentile: 1.2873503684997558
50th percentile: 1.292797565460205
60th percentile: 1.2933951377868653
70th percentile: 1.2939927101135253
80th percentile: 1.4642891407012941
90th percentile: 1.804284429550171
95th percentile: 1.9742820739746092
99th percentile: 2.1102801895141603
mean time: 1.4575785160064698
Pipeline stage StressChecker completed in 8.07s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.02s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
cgato-l3-thespice-8b-dpo_2839_v3 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dpo_2839_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics