submission_id: cgato-l3-thespice-8b-dp_2839_v10
developer_uid: c.gato
status: torndown
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e8.1
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', '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: 2024-05-23T13:38:06+00:00
model_name: cgato-l3-thespice-8b-dp_2839_v10
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 15636
num_wins: 8258
celo_rating: 1197.78
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-dp_2839_v10
ineligible_reason: propriety_total_count < 800
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e8.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-23
win_ratio: 0.528140189306728
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dp-2839-v10-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dp-2839-v10-mkmlizer to finish
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dp-2839-v10-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-2839-v10-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: Downloaded to shared memory in 17.135s
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 66.15it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 79.58it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 117.72it/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-2839-v10-mkmlizer: quantized model in 23.732s
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e8.1 in 42.138s
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-2839-v10
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-2839-v10/special_tokens_map.json
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-2839-v10/config.json
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-2839-v10/tokenizer_config.json
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-2839-v10/tokenizer.json
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-2839-v10/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dp-2839-v10-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-2839-v10-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-2839-v10-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-2839-v10-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-2839-v10-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-2839-v10-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: Saving duration: 0.308s
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.312s
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-2839-v10_reward
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-2839-v10_reward/config.json
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-2839-v10_reward/merges.txt
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-2839-v10_reward/tokenizer_config.json
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-2839-v10_reward/special_tokens_map.json
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-2839-v10_reward/vocab.json
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-2839-v10_reward/tokenizer.json
cgato-l3-thespice-8b-dp-2839-v10-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-2839-v10_reward/reward.tensors
Job cgato-l3-thespice-8b-dp-2839-v10-mkmlizer completed after 65.11s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dp-2839-v10-mkmlizer
Pipeline stage MKMLizer completed in 70.11s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dp-2839-v10
Waiting for inference service cgato-l3-thespice-8b-dp-2839-v10 to be ready
Inference service cgato-l3-thespice-8b-dp-2839-v10 ready after 49.573479890823364s
Pipeline stage ISVCDeployer completed in 58.48s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.133280038833618s
Received healthy response to inference request in 1.3116495609283447s
Received healthy response to inference request in 1.2664515972137451s
Received healthy response to inference request in 1.2566521167755127s
Received healthy response to inference request in 1.265125036239624s
5 requests
0 failed requests
5th percentile: 1.2583467006683349
10th percentile: 1.2600412845611573
20th percentile: 1.2634304523468018
30th percentile: 1.2653903484344482
40th percentile: 1.2659209728240968
50th percentile: 1.2664515972137451
60th percentile: 1.2845307826995849
70th percentile: 1.3026099681854248
80th percentile: 1.4759756565093995
90th percentile: 1.804627847671509
95th percentile: 1.9689539432525633
99th percentile: 2.100414819717407
mean time: 1.446631669998169
Pipeline stage StressChecker completed in 7.90s
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_2839_v10 status is now deployed due to DeploymentManager action
Scoring model output for bot %s
cgato-l3-thespice-8b-dp_2839_v10 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-dp_2839_v10
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-dp-2839-v10 is running
Tearing down inference service cgato-l3-thespice-8b-dp-2839-v10
Toredown service cgato-l3-thespice-8b-dp-2839-v10
Pipeline stage ISVCDeleter completed in 5.07s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dp-2839-v10/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dp-2839-v10/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dp-2839-v10/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dp-2839-v10/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dp-2839-v10/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dp-2839-v10_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dp-2839-v10_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dp-2839-v10_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dp-2839-v10_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dp-2839-v10_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dp-2839-v10_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dp-2839-v10_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.58s
cgato-l3-thespice-8b-dp_2839_v10 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics