submission_id: cgato-l3-thespice-8b-dpo_8705_v3
developer_uid: c.gato
status: torndown
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e16.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, '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: 2024-06-04T17:42:33+00:00
model_name: cgato-l3-thespice-8b-dpo_8705_v3
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 9114
num_wins: 4677
celo_rating: 1197.0
propriety_score: 0.6600985221674877
propriety_total_count: 203.0
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_8705_v3
ineligible_reason: propriety_total_count < 800
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e16.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-04
win_ratio: 0.5131665569453588
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer to finish
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-8705-v3-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-8705-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: Downloaded to shared memory in 15.799s
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 80.32it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 92.50it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 132.29it/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-8705-v3-mkmlizer: quantized model in 23.442s
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e16.1 in 41.721s
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8705-v3
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8705-v3/tokenizer_config.json
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8705-v3/special_tokens_map.json
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8705-v3/config.json
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8705-v3/tokenizer.json
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-8705-v3/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-8705-v3-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-8705-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-8705-v3-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-8705-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-8705-v3-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-8705-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-8705-v3-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-8705-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: Saving duration: 0.381s
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.334s
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8705-v3_reward
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8705-v3_reward/config.json
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8705-v3_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8705-v3_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8705-v3_reward/merges.txt
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8705-v3_reward/vocab.json
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8705-v3_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-8705-v3_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer completed after 73.24s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-8705-v3-mkmlizer
Pipeline stage MKMLizer completed in 77.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-8705-v3
Waiting for inference service cgato-l3-thespice-8b-dpo-8705-v3 to be ready
Inference service cgato-l3-thespice-8b-dpo-8705-v3 ready after 30.338566064834595s
Pipeline stage ISVCDeployer completed in 38.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 12.615445613861084s
Received healthy response to inference request in 1.29058837890625s
Received healthy response to inference request in 1.3306303024291992s
Received healthy response to inference request in 1.3142201900482178s
Received healthy response to inference request in 1.283524513244629s
5 requests
0 failed requests
5th percentile: 1.284937286376953
10th percentile: 1.2863500595092774
20th percentile: 1.2891756057739259
30th percentile: 1.2953147411346435
40th percentile: 1.3047674655914308
50th percentile: 1.3142201900482178
60th percentile: 1.3207842350006103
70th percentile: 1.327348279953003
80th percentile: 3.587593364715578
90th percentile: 8.101519489288332
95th percentile: 10.358482551574705
99th percentile: 12.164053001403808
mean time: 3.566881799697876
Pipeline stage StressChecker completed in 18.57s
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-dpo_8705_v3 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_8705_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-dpo_8705_v3
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-dpo-8705-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.76s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-8705-v3/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-8705-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-8705-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-8705-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-8705-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-8705-v3_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-8705-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-8705-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-8705-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-8705-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-8705-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-8705-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.56s
cgato-l3-thespice-8b-dpo_8705_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics