submission_id: cgato-l3-thespice-8b-dp_3142_v15
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e13.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, '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: 2024-06-01T11:57:46+00:00
model_name: cgato-l3-thespice-8b-dp_3142_v15
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 11762
num_wins: 6415
celo_rating: 1211.61
safety_score: 0.92
propriety_score: 0.7777777777777778
propriety_total_count: 9.0
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-dp_3142_v15
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e13.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.5454004421016834
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dp-3142-v15-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dp-3142-v15-mkmlizer to finish
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dp-3142-v15-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-dp-3142-v15-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: Downloaded to shared memory in 13.177s
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 97.54it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:00, 114.07it/s] Loading 0: 99%|█████████▊| 287/291 [00:01<00:00, 162.45it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: quantized model in 16.971s
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e13.2 in 31.075s
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v15
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v15/config.json
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v15/special_tokens_map.json
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v15/tokenizer_config.json
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v15/tokenizer.json
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v15/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dp-3142-v15-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-dp-3142-v15-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v15-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-dp-3142-v15-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v15-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-dp-3142-v15-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v15-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-dp-3142-v15-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: Saving duration: 0.229s
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.393s
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v15_reward
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v15_reward/special_tokens_map.json
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v15_reward/tokenizer_config.json
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v15_reward/config.json
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v15_reward/merges.txt
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v15_reward/vocab.json
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v15_reward/tokenizer.json
cgato-l3-thespice-8b-dp-3142-v15-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v15_reward/reward.tensors
Job cgato-l3-thespice-8b-dp-3142-v15-mkmlizer completed after 52.4s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dp-3142-v15-mkmlizer
Pipeline stage MKMLizer completed in 54.80s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dp-3142-v15
Waiting for inference service cgato-l3-thespice-8b-dp-3142-v15 to be ready
Inference service cgato-l3-thespice-8b-dp-3142-v15 ready after 60.30759930610657s
Pipeline stage ISVCDeployer completed in 67.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.226961135864258s
Received healthy response to inference request in 1.3117482662200928s
Received healthy response to inference request in 1.3123512268066406s
Received healthy response to inference request in 1.2834880352020264s
Received healthy response to inference request in 1.2756547927856445s
5 requests
0 failed requests
5th percentile: 1.277221441268921
10th percentile: 1.2787880897521973
20th percentile: 1.28192138671875
30th percentile: 1.2891400814056397
40th percentile: 1.3004441738128663
50th percentile: 1.3117482662200928
60th percentile: 1.3119894504547118
70th percentile: 1.312230634689331
80th percentile: 1.4952732086181642
90th percentile: 1.861117172241211
95th percentile: 2.0440391540527343
99th percentile: 2.190376739501953
mean time: 1.4820406913757325
Pipeline stage StressChecker completed in 8.07s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dp_3142_v15 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dp_3142_v15 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics