submission_id: cgato-l3-thespice-8b-dp_3142_v12
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', '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: 2024-05-31T23:27:21+00:00
model_name: cgato-l3-thespice-8b-dp_3142_v12
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 7414
num_wins: 4046
celo_rating: 1210.09
propriety_score: 0.0
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_v12
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: 0.5457243053682223
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dp-3142-v12-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dp-3142-v12-mkmlizer to finish
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dp-3142-v12-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-v12-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: Downloaded to shared memory in 17.267s
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 71.28it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 88.16it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 128.92it/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-v12-mkmlizer: quantized model in 23.740s
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e13.2 in 43.650s
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v12
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v12/config.json
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v12/tokenizer_config.json
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v12/special_tokens_map.json
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v12/tokenizer.json
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v12/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dp-3142-v12-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-v12-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v12-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-v12-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v12-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-v12-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v12-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-v12-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: Saving duration: 0.398s
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.332s
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v12_reward
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v12_reward/config.json
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v12_reward/tokenizer_config.json
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v12_reward/special_tokens_map.json
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v12_reward/merges.txt
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v12_reward/vocab.json
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v12_reward/tokenizer.json
cgato-l3-thespice-8b-dp-3142-v12-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v12_reward/reward.tensors
Job cgato-l3-thespice-8b-dp-3142-v12-mkmlizer completed after 73.49s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dp-3142-v12-mkmlizer
Pipeline stage MKMLizer completed in 76.71s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dp-3142-v12
Waiting for inference service cgato-l3-thespice-8b-dp-3142-v12 to be ready
Inference service cgato-l3-thespice-8b-dp-3142-v12 ready after 40.200997829437256s
Pipeline stage ISVCDeployer completed in 47.47s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2098586559295654s
Received healthy response to inference request in 1.289290428161621s
Received healthy response to inference request in 1.3026528358459473s
Received healthy response to inference request in 1.288759708404541s
Received healthy response to inference request in 1.2770898342132568s
5 requests
0 failed requests
5th percentile: 1.2794238090515138
10th percentile: 1.2817577838897705
20th percentile: 1.286425733566284
30th percentile: 1.288865852355957
40th percentile: 1.289078140258789
50th percentile: 1.289290428161621
60th percentile: 1.2946353912353517
70th percentile: 1.299980354309082
80th percentile: 1.484093999862671
90th percentile: 1.8469763278961182
95th percentile: 2.0284174919128417
99th percentile: 2.1735704231262205
mean time: 1.4735302925109863
Pipeline stage StressChecker completed in 8.00s
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_v12 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dp_3142_v12 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics