submission_id: cgato-l3-thespice-8b-dp_3142_v11
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': 0.75, 'top_p': 1.0, 'min_p': 0.05, '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{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{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: 2024-05-31T18:11:48+00:00
model_name: cgato-l3-thespice-8b-dp_3142_v11
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 9386
num_wins: 5066
celo_rating: 1204.32
safety_score: 0.86
propriety_score: 1.0
propriety_total_count: 1.0
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_v11
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: 2024-05-31
win_ratio: 0.5397400383549968
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dp-3142-v11-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dp-3142-v11-mkmlizer to finish
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dp-3142-v11-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-v11-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: Downloaded to shared memory in 14.425s
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 94.41it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:00, 108.13it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 154.75it/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-v11-mkmlizer: quantized model in 17.690s
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e13.2 in 33.096s
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v11
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v11/config.json
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v11/special_tokens_map.json
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v11/tokenizer_config.json
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v11/tokenizer.json
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v11/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dp-3142-v11-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-v11-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v11-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-v11-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v11-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-v11-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v11-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-v11-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: Saving duration: 0.243s
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.122s
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v11_reward
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v11_reward/special_tokens_map.json
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v11_reward/config.json
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v11_reward/tokenizer_config.json
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v11_reward/merges.txt
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v11_reward/vocab.json
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v11_reward/tokenizer.json
cgato-l3-thespice-8b-dp-3142-v11-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v11_reward/reward.tensors
Job cgato-l3-thespice-8b-dp-3142-v11-mkmlizer completed after 63.71s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dp-3142-v11-mkmlizer
Pipeline stage MKMLizer completed in 67.09s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dp-3142-v11
Waiting for inference service cgato-l3-thespice-8b-dp-3142-v11 to be ready
Inference service cgato-l3-thespice-8b-dp-3142-v11 ready after 50.31313681602478s
Pipeline stage ISVCDeployer completed in 57.66s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3623268604278564s
Received healthy response to inference request in 1.3208537101745605s
Received healthy response to inference request in 1.299351453781128s
Received healthy response to inference request in 1.3078720569610596s
Received healthy response to inference request in 1.3110523223876953s
5 requests
0 failed requests
5th percentile: 1.3010555744171142
10th percentile: 1.3027596950531006
20th percentile: 1.3061679363250733
30th percentile: 1.3085081100463867
40th percentile: 1.309780216217041
50th percentile: 1.3110523223876953
60th percentile: 1.3149728775024414
70th percentile: 1.3188934326171875
80th percentile: 1.52914834022522
90th percentile: 1.945737600326538
95th percentile: 2.1540322303771973
99th percentile: 2.320667934417725
mean time: 1.52029128074646
Pipeline stage StressChecker completed in 8.52s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
cgato-l3-thespice-8b-dp_3142_v11 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dp_3142_v11 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics