submission_id: cgato-l3-thespice-8b-dp_3142_v17
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': 0.025, '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: 2024-06-01T12:58:09+00:00
model_name: cgato-l3-thespice-8b-dp_3142_v17
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 9987
num_wins: 5385
celo_rating: 1213.36
safety_score: 0.94
propriety_score: 0.5
propriety_total_count: 2.0
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_v17
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: 0.5392009612496245
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dp-3142-v17-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dp-3142-v17-mkmlizer to finish
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dp-3142-v17-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-v17-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: Downloaded to shared memory in 18.053s
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 81.81it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 83.51it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 122.52it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: quantized model in 23.982s
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v17
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v17/config.json
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v17/tokenizer_config.json
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v17/special_tokens_map.json
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v17/tokenizer.json
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v17/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dp-3142-v17-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-v17-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v17-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-v17-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v17-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-v17-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v17-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-v17-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: Saving duration: 0.401s
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.082s
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v17_reward
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v17_reward/special_tokens_map.json
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v17_reward/tokenizer_config.json
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v17_reward/config.json
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v17_reward/merges.txt
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v17_reward/vocab.json
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v17_reward/tokenizer.json
cgato-l3-thespice-8b-dp-3142-v17-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v17_reward/reward.tensors
Job cgato-l3-thespice-8b-dp-3142-v17-mkmlizer completed after 72.97s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dp-3142-v17-mkmlizer
Pipeline stage MKMLizer completed in 73.30s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dp-3142-v17
Waiting for inference service cgato-l3-thespice-8b-dp-3142-v17 to be ready
Inference service cgato-l3-thespice-8b-dp-3142-v17 ready after 100.62179636955261s
Pipeline stage ISVCDeployer completed in 106.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2688100337982178s
Received healthy response to inference request in 1.3177828788757324s
Received healthy response to inference request in 1.3419466018676758s
Received healthy response to inference request in 1.3180193901062012s
Received healthy response to inference request in 1.2899694442749023s
5 requests
0 failed requests
5th percentile: 1.2955321311950683
10th percentile: 1.3010948181152344
20th percentile: 1.3122201919555665
30th percentile: 1.3178301811218263
40th percentile: 1.3179247856140137
50th percentile: 1.3180193901062012
60th percentile: 1.327590274810791
70th percentile: 1.337161159515381
80th percentile: 1.5273192882537843
90th percentile: 1.898064661026001
95th percentile: 2.0834373474121093
99th percentile: 2.231735496520996
mean time: 1.507305669784546
Pipeline stage StressChecker completed in 8.19s
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_v17 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dp_3142_v17 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics