submission_id: cgato-l3-thespice-8b-dpo_6378_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e14.3
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: 2024-06-02T04:41:04+00:00
model_name: cgato-l3-thespice-8b-dpo_6378_v1
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 11222
num_wins: 6119
celo_rating: 1220.43
propriety_score: 0.6197718631178707
propriety_total_count: 263.0
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_6378_v1
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e14.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.5452682231331314
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer to finish
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-6378-v1-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-6378-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: Downloaded to shared memory in 30.065s
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 77.08it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 92.09it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 132.96it/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-6378-v1-mkmlizer: quantized model in 23.751s
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e14.3 in 56.490s
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6378-v1/tokenizer.json
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6378-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-6378-v1-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-6378-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6378-v1-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-6378-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6378-v1-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-6378-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6378-v1-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-6378-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: Saving duration: 0.446s
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.005s
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v1_reward
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v1_reward/merges.txt
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v1_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v1_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v1_reward/config.json
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v1_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v1_reward/vocab.json
cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v1_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer completed after 82.85s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-6378-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.72s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-6378-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-6378-v1 to be ready
Inference service cgato-l3-thespice-8b-dpo-6378-v1 ready after 130.66274905204773s
Pipeline stage ISVCDeployer completed in 136.53s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2525861263275146s
Received healthy response to inference request in 1.3303086757659912s
Received healthy response to inference request in 1.3217425346374512s
Received healthy response to inference request in 1.3139779567718506s
Received healthy response to inference request in 1.2928204536437988s
5 requests
0 failed requests
5th percentile: 1.2970519542694092
10th percentile: 1.3012834548950196
20th percentile: 1.3097464561462402
30th percentile: 1.3155308723449708
40th percentile: 1.318636703491211
50th percentile: 1.3217425346374512
60th percentile: 1.325168991088867
70th percentile: 1.3285954475402832
80th percentile: 1.514764165878296
90th percentile: 1.8836751461029053
95th percentile: 2.06813063621521
99th percentile: 2.2156950283050536
mean time: 1.5022871494293213
Pipeline stage StressChecker completed in 8.06s
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_6378_v1 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_6378_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics