submission_id: hastagaras-llama3-8b-dar_7411_v6
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/llama3-8b-darktune-KTO
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.1, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this uncensored fictional roleplay with {user_name}.\n\n{memory}\n\n", 'prompt_template': 'Notes for {user_name}: {prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-05-12T02:24:42+00:00
model_name: drktune-kto-test
model_eval_status: success
model_group: Hastagaras/llama3-8b-dar
num_battles: 9019
num_wins: 4743
celo_rating: 1182.6
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: drktune-kto-test
ineligible_reason: propriety_total_count < 800
language_model: Hastagaras/llama3-8b-darktune-KTO
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-11
win_ratio: 0.5258897882248587
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-8b-dar-7411-v6-mkmlizer
Waiting for job on hastagaras-llama3-8b-dar-7411-v6-mkmlizer to finish
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ _____ __ __ ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ /___/ ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ belonging to: ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ║ ║
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-8b-dar-7411-v6-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.
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 44%|████▍ | 129/291 [00:00<00:01, 129.08it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 132.47it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 29.30it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: quantized model in 17.673s
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: Processed model Hastagaras/llama3-8b-darktune-KTO in 33.603s
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v6
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v6/tokenizer_config.json
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v6/special_tokens_map.json
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v6/config.json
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v6/tokenizer.json
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-8b-dar-7411-v6/flywheel_model.0.safetensors
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-8b-dar-7411-v6-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.
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: warnings.warn(
hastagaras-llama3-8b-dar-7411-v6-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.
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: warnings.warn(
hastagaras-llama3-8b-dar-7411-v6-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.
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: warnings.warn(
hastagaras-llama3-8b-dar-7411-v6-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()
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: Saving duration: 0.241s
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.302s
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v6_reward
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v6_reward/config.json
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v6_reward/merges.txt
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v6_reward/special_tokens_map.json
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v6_reward/tokenizer_config.json
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v6_reward/vocab.json
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v6_reward/tokenizer.json
hastagaras-llama3-8b-dar-7411-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-8b-dar-7411-v6_reward/reward.tensors
Job hastagaras-llama3-8b-dar-7411-v6-mkmlizer completed after 62.95s with status: succeeded
Stopping job with name hastagaras-llama3-8b-dar-7411-v6-mkmlizer
Pipeline stage MKMLizer completed in 67.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-8b-dar-7411-v6
Waiting for inference service hastagaras-llama3-8b-dar-7411-v6 to be ready
Inference service hastagaras-llama3-8b-dar-7411-v6 ready after 30.192442893981934s
Pipeline stage ISVCDeployer completed in 37.65s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3224809169769287s
Received healthy response to inference request in 1.3296496868133545s
Received healthy response to inference request in 1.2905197143554688s
%s, retrying in %s seconds...
Received healthy response to inference request in 1.4129445552825928s
Received healthy response to inference request in 1.3279030323028564s
Received healthy response to inference request in 1.3030564785003662s
Received healthy response to inference request in 1.2777516841888428s
Received healthy response to inference request in 1.321650505065918s
5 requests
0 failed requests
5th percentile: 1.2828126430511475
10th percentile: 1.2878736019134522
20th percentile: 1.2979955196380615
30th percentile: 1.3067752838134765
40th percentile: 1.3142128944396974
50th percentile: 1.321650505065918
60th percentile: 1.3241515159606934
70th percentile: 1.3266525268554688
80th percentile: 1.3449113368988037
90th percentile: 1.3789279460906982
95th percentile: 1.3959362506866455
99th percentile: 1.4095428943634034
mean time: 1.3286612510681153
Pipeline stage StressChecker completed in 32.27s
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
hastagaras-llama3-8b-dar_7411_v6 status is now deployed due to DeploymentManager action
hastagaras-llama3-8b-dar_7411_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-8b-dar_7411_v6
Running pipeline stage ISVCDeleter
Deleting key hastagaras-llama-3-8b-ouch-v1/special_tokens_map.json from bucket guanaco-mkml-models
Checking if service hastagaras-llama3-8b-dar-7411-v6 is running
Deleting key hastagaras-llama-3-8b-ouch-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ouch-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-ouch-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.32s
hastagaras-llama-3-8b-ouch_v1 status is now torndown due to DeploymentManager action
Tearing down inference service hastagaras-llama3-8b-dar-7411-v6
Toredown service hastagaras-llama3-8b-dar-7411-v6
Pipeline stage ISVCDeleter completed in 6.45s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-dar-7411-v6/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7411-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7411-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7411-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-dar-7411-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-dar-7411-v6_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-dar-7411-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.17s
hastagaras-llama3-8b-dar_7411_v6 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics