submission_id: cgato-l3-thespice-8b-dp_3142_v16
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': 0.15, '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: 2024-06-01T12:28:46+00:00
model_name: cgato-l3-thespice-8b-dp_3142_v16
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 7726
num_wins: 4200
celo_rating: 1211.59
safety_score: 0.93
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_v16
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: 0.5436189490033653
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dp-3142-v16-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dp-3142-v16-mkmlizer to finish
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dp-3142-v16-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-v16-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: Downloaded to shared memory in 18.107s
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 80.87it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 83.17it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 124.43it/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-v16-mkmlizer: quantized model in 23.763s
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e13.2 in 44.417s
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v16
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v16/config.json
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v16/tokenizer_config.json
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v16/special_tokens_map.json
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v16/tokenizer.json
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v16/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dp-3142-v16-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-v16-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v16-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-v16-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v16-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-v16-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v16-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-v16-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v16_reward
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v16_reward/special_tokens_map.json
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v16_reward/config.json
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v16_reward/vocab.json
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v16_reward/tokenizer_config.json
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v16_reward/tokenizer.json
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v16_reward/merges.txt
cgato-l3-thespice-8b-dp-3142-v16-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v16_reward/reward.tensors
Job cgato-l3-thespice-8b-dp-3142-v16-mkmlizer completed after 72.96s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dp-3142-v16-mkmlizer
Pipeline stage MKMLizer completed in 73.99s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dp-3142-v16
Waiting for inference service cgato-l3-thespice-8b-dp-3142-v16 to be ready
Inference service cgato-l3-thespice-8b-dp-3142-v16 ready after 40.23256492614746s
Pipeline stage ISVCDeployer completed in 46.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2951998710632324s
Received healthy response to inference request in 1.316499948501587s
Received healthy response to inference request in 1.3117880821228027s
Received healthy response to inference request in 1.2862133979797363s
Received healthy response to inference request in 1.273113489151001s
5 requests
0 failed requests
5th percentile: 1.275733470916748
10th percentile: 1.2783534526824951
20th percentile: 1.2835934162139893
30th percentile: 1.2913283348083495
40th percentile: 1.3015582084655761
50th percentile: 1.3117880821228027
60th percentile: 1.3136728286743165
70th percentile: 1.3155575752258302
80th percentile: 1.5122399330139162
90th percentile: 1.9037199020385742
95th percentile: 2.0994598865509033
99th percentile: 2.2560518741607667
mean time: 1.4965629577636719
Pipeline stage StressChecker completed in 8.11s
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-dp_3142_v16 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dp_3142_v16 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics