submission_id: undi95-llama-3-lewdplay-_3862_v7
developer_uid: alexdaoud
status: torndown
model_repo: Undi95/Llama-3-LewdPlay-8B-evo
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, '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': False}
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': False}
timestamp: 2024-05-14T22:36:50+00:00
model_name: undi95-llama-3-lewdplay-_3862_v7
model_eval_status: success
model_group: Undi95/Llama-3-LewdPlay-
num_battles: 11350
num_wins: 5337
celo_rating: 1162.88
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: undi95-llama-3-lewdplay-_3862_v7
ineligible_reason: propriety_total_count < 800
language_model: Undi95/Llama-3-LewdPlay-8B-evo
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-14
win_ratio: 0.4702202643171806
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name undi95-llama-3-lewdplay-3862-v7-mkmlizer
Waiting for job on undi95-llama-3-lewdplay-3862-v7-mkmlizer to finish
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ _____ __ __ ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ /___/ ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ Version: 0.8.14 ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ https://mk1.ai ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ The license key for the current software has been verified as ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ belonging to: ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ Chai Research Corp. ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ║ ║
undi95-llama-3-lewdplay-3862-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
undi95-llama-3-lewdplay-3862-v7-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.
undi95-llama-3-lewdplay-3862-v7-mkmlizer: warnings.warn(warning_message, FutureWarning)
undi95-llama-3-lewdplay-3862-v7-mkmlizer: Downloaded to shared memory in 10.933s
undi95-llama-3-lewdplay-3862-v7-mkmlizer: quantizing model to /dev/shm/model_cache
undi95-llama-3-lewdplay-3862-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
undi95-llama-3-lewdplay-3862-v7-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:58, 2.07s/it] Loading 0: 8%|▊ | 22/291 [00:04<00:37, 7.13it/s] Loading 0: 14%|█▍ | 42/291 [00:04<00:15, 15.81it/s] Loading 0: 23%|██▎ | 67/291 [00:04<00:07, 29.93it/s] Loading 0: 30%|██▉ | 87/291 [00:04<00:04, 43.19it/s] Loading 0: 38%|███▊ | 112/291 [00:04<00:02, 63.71it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:01, 81.01it/s] Loading 0: 54%|█████▍ | 157/291 [00:04<00:01, 104.45it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:01, 65.68it/s] Loading 0: 69%|██████▉ | 202/291 [00:05<00:01, 85.66it/s] Loading 0: 76%|███████▋ | 222/291 [00:05<00:00, 100.92it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 125.53it/s] Loading 0: 92%|█████████▏| 267/291 [00:05<00:00, 137.68it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
undi95-llama-3-lewdplay-3862-v7-mkmlizer: quantized model in 17.307s
undi95-llama-3-lewdplay-3862-v7-mkmlizer: Processed model Undi95/Llama-3-LewdPlay-8B-evo in 29.290s
undi95-llama-3-lewdplay-3862-v7-mkmlizer: creating bucket guanaco-mkml-models
undi95-llama-3-lewdplay-3862-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
undi95-llama-3-lewdplay-3862-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v7
undi95-llama-3-lewdplay-3862-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v7/special_tokens_map.json
undi95-llama-3-lewdplay-3862-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v7/tokenizer_config.json
undi95-llama-3-lewdplay-3862-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v7/config.json
undi95-llama-3-lewdplay-3862-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v7/tokenizer.json
undi95-llama-3-lewdplay-3862-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v7/flywheel_model.0.safetensors
undi95-llama-3-lewdplay-3862-v7-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
undi95-llama-3-lewdplay-3862-v7-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.
undi95-llama-3-lewdplay-3862-v7-mkmlizer: warnings.warn(
undi95-llama-3-lewdplay-3862-v7-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.
undi95-llama-3-lewdplay-3862-v7-mkmlizer: warnings.warn(
undi95-llama-3-lewdplay-3862-v7-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()
undi95-llama-3-lewdplay-3862-v7-mkmlizer: return self.fget.__get__(instance, owner)()
undi95-llama-3-lewdplay-3862-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
undi95-llama-3-lewdplay-3862-v7-mkmlizer: Saving duration: 0.242s
undi95-llama-3-lewdplay-3862-v7-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.299s
undi95-llama-3-lewdplay-3862-v7-mkmlizer: creating bucket guanaco-reward-models
undi95-llama-3-lewdplay-3862-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
undi95-llama-3-lewdplay-3862-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v7_reward
undi95-llama-3-lewdplay-3862-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v7_reward/special_tokens_map.json
undi95-llama-3-lewdplay-3862-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v7_reward/merges.txt
undi95-llama-3-lewdplay-3862-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v7_reward/vocab.json
undi95-llama-3-lewdplay-3862-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v7_reward/tokenizer_config.json
undi95-llama-3-lewdplay-3862-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v7_reward/config.json
undi95-llama-3-lewdplay-3862-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v7_reward/tokenizer.json
undi95-llama-3-lewdplay-3862-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v7_reward/reward.tensors
Job undi95-llama-3-lewdplay-3862-v7-mkmlizer completed after 53.03s with status: succeeded
Stopping job with name undi95-llama-3-lewdplay-3862-v7-mkmlizer
Pipeline stage MKMLizer completed in 57.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service undi95-llama-3-lewdplay-3862-v7
Waiting for inference service undi95-llama-3-lewdplay-3862-v7 to be ready
Inference service undi95-llama-3-lewdplay-3862-v7 ready after 40.28066658973694s
Pipeline stage ISVCDeployer completed in 47.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9550690650939941s
Received healthy response to inference request in 1.1147327423095703s
Received healthy response to inference request in 1.1418168544769287s
Received healthy response to inference request in 1.1240127086639404s
Received healthy response to inference request in 1.1161582469940186s
5 requests
0 failed requests
5th percentile: 1.11501784324646
10th percentile: 1.1153029441833495
20th percentile: 1.115873146057129
30th percentile: 1.1177291393280029
40th percentile: 1.1208709239959718
50th percentile: 1.1240127086639404
60th percentile: 1.1311343669891358
70th percentile: 1.138256025314331
80th percentile: 1.3044672966003419
90th percentile: 1.629768180847168
95th percentile: 1.792418622970581
99th percentile: 1.9225389766693115
mean time: 1.2903579235076905
Pipeline stage StressChecker completed in 7.12s
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
undi95-llama-3-lewdplay-_3862_v7 status is now deployed due to DeploymentManager action
undi95-llama-3-lewdplay-_3862_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of undi95-llama-3-lewdplay-_3862_v7
Running pipeline stage ISVCDeleter
Checking if service undi95-llama-3-lewdplay-3862-v7 is running
Tearing down inference service undi95-llama-3-lewdplay-3862-v7
Toredown service undi95-llama-3-lewdplay-3862-v7
Pipeline stage ISVCDeleter completed in 3.42s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key undi95-llama-3-lewdplay-3862-v7/config.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-3862-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-3862-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-3862-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key undi95-llama-3-lewdplay-3862-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key undi95-llama-3-lewdplay-3862-v7_reward/config.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key undi95-llama-3-lewdplay-3862-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.85s
undi95-llama-3-lewdplay-_3862_v7 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics