submission_id: cgato-l3-thespice-8b-dpo_3142_v5
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': 0.9, 'top_p': 0.9, '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: 2024-05-31T14:07:37+00:00
model_name: cgato-l3-thespice-8b-dpo_3142_v5
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 9646
num_wins: 5221
celo_rating: 1214.61
safety_score: 0.84
propriety_score: 1.0
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-dpo_3142_v5
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: 0.5412606261662866
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer to finish
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-3142-v5-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-dpo-3142-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: Downloaded to shared memory in 43.439s
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 60.66it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 75.11it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 110.00it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: quantized model in 24.234s
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e13.2 in 70.113s
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3142-v5
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3142-v5/tokenizer_config.json
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3142-v5/config.json
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3142-v5/special_tokens_map.json
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3142-v5/tokenizer.json
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3142-v5/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-3142-v5-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-dpo-3142-v5-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-3142-v5-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-dpo-3142-v5-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-3142-v5-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-dpo-3142-v5-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-3142-v5-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-dpo-3142-v5-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: Saving duration: 0.453s
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.914s
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v5_reward
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v5_reward/config.json
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v5_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v5_reward/merges.txt
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v5_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v5_reward/vocab.json
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v5_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3142-v5_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer completed after 103.94s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-3142-v5-mkmlizer
Pipeline stage MKMLizer completed in 104.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-3142-v5
Waiting for inference service cgato-l3-thespice-8b-dpo-3142-v5 to be ready
Inference service cgato-l3-thespice-8b-dpo-3142-v5 ready after 40.24571919441223s
Pipeline stage ISVCDeployer completed in 47.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2898855209350586s
Received healthy response to inference request in 4.383351564407349s
Received healthy response to inference request in 1.3021965026855469s
Received healthy response to inference request in 1.2904751300811768s
Received healthy response to inference request in 1.3043091297149658s
5 requests
0 failed requests
5th percentile: 1.2928194046020507
10th percentile: 1.2951636791229248
20th percentile: 1.299852228164673
30th percentile: 1.3026190280914307
40th percentile: 1.3034640789031982
50th percentile: 1.3043091297149658
60th percentile: 1.6985396862030029
70th percentile: 2.09277024269104
80th percentile: 2.708578729629517
90th percentile: 3.545965147018433
95th percentile: 3.9646583557128903
99th percentile: 4.299612922668457
mean time: 2.1140435695648194
Pipeline stage StressChecker completed in 11.18s
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-dpo_3142_v5 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_3142_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics