submission_id: cgato-l3-thespice-8b-dpo_1354_v2
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e7.2
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': "<|im_start|>system\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|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: 2024-05-22T02:38:12+00:00
model_name: cgato-l3-thespice-8b-dpo_1354_v2
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 13296
num_wins: 7196
celo_rating: 1203.78
safety_score: 0.9
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_1354_v2
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e7.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-21
win_ratio: 0.5412154031287605
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer to finish
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-1354-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-1354-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: Downloaded to shared memory in 15.001s
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 86.52it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 103.40it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 147.98it/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-1354-v2-mkmlizer: quantized model in 17.584s
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e7.2 in 33.612s
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-1354-v2
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-1354-v2/config.json
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-1354-v2/special_tokens_map.json
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-1354-v2/tokenizer_config.json
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-1354-v2/tokenizer.json
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-1354-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-1354-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-1354-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-1354-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-1354-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-1354-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-1354-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-1354-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-1354-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: Saving duration: 0.256s
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.577s
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-1354-v2_reward
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-1354-v2_reward/config.json
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-1354-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-1354-v2_reward/merges.txt
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-1354-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-1354-v2_reward/vocab.json
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-1354-v2_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-1354-v2_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer completed after 62.86s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-1354-v2-mkmlizer
Pipeline stage MKMLizer completed in 65.83s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-1354-v2
Waiting for inference service cgato-l3-thespice-8b-dpo-1354-v2 to be ready
Inference service cgato-l3-thespice-8b-dpo-1354-v2 ready after 60.41795563697815s
Pipeline stage ISVCDeployer completed in 67.20s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.224696636199951s
Received healthy response to inference request in 1.3161303997039795s
Received healthy response to inference request in 1.2962257862091064s
Received healthy response to inference request in 1.2845432758331299s
Received healthy response to inference request in 1.2854979038238525s
5 requests
0 failed requests
5th percentile: 1.2847342014312744
10th percentile: 1.2849251270294189
20th percentile: 1.285306978225708
30th percentile: 1.2876434803009034
40th percentile: 1.2919346332550048
50th percentile: 1.2962257862091064
60th percentile: 1.3041876316070558
70th percentile: 1.3121494770050048
80th percentile: 1.497843647003174
90th percentile: 1.8612701416015627
95th percentile: 2.0429833889007565
99th percentile: 2.188353986740112
mean time: 1.4814188003540039
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_1354_v2 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_1354_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics