submission_id: cgato-l3-thespice-8b-dpo_2804_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e12.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, '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': "{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}
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: 2024-05-29T02:12:29+00:00
model_name: cgato-l3-thespice-8b-dpo_2804_v1
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 9016
num_wins: 4853
celo_rating: 1202.71
safety_score: 0.92
propriety_score: 0.0
propriety_total_count: 0.0
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_2804_v1
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e12.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-28
win_ratio: 0.5382653061224489
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer to finish
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-2804-v1-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-2804-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: Downloaded to shared memory in 35.083s
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 80.15it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 94.90it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 135.95it/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-2804-v1-mkmlizer: quantized model in 23.384s
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e12.1 in 61.064s
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2804-v1
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2804-v1/config.json
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2804-v1/special_tokens_map.json
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2804-v1/tokenizer_config.json
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2804-v1/tokenizer.json
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-2804-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-2804-v1-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-2804-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-2804-v1-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-2804-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-2804-v1-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-2804-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-2804-v1-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-2804-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: Saving duration: 0.418s
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.234s
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2804-v1_reward
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2804-v1_reward/config.json
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2804-v1_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2804-v1_reward/merges.txt
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2804-v1_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2804-v1_reward/vocab.json
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2804-v1_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-2804-v1_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer completed after 83.58s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-2804-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.84s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-2804-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-2804-v1 to be ready
Inference service cgato-l3-thespice-8b-dpo-2804-v1 ready after 40.22790861129761s
Pipeline stage ISVCDeployer completed in 47.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.074755907058716s
Received healthy response to inference request in 1.24462890625s
Received healthy response to inference request in 1.2492938041687012s
Received healthy response to inference request in 1.2739789485931396s
Received healthy response to inference request in 1.2239949703216553s
5 requests
0 failed requests
5th percentile: 1.2281217575073242
10th percentile: 1.2322485446929932
20th percentile: 1.240502119064331
30th percentile: 1.2455618858337403
40th percentile: 1.2474278450012206
50th percentile: 1.2492938041687012
60th percentile: 1.2591678619384765
70th percentile: 1.2690419197082519
80th percentile: 1.434134340286255
90th percentile: 1.7544451236724854
95th percentile: 1.9146005153656005
99th percentile: 2.0427248287200928
mean time: 1.4133305072784423
Pipeline stage StressChecker completed in 7.69s
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_2804_v1 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_2804_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics