submission_id: sao10k-l3-rp-v3-3_v4
developer_uid: sao10k
best_of: 8
celo_rating: 1213.02
display_name: V3-Private-Neph-Custom-1
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{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}
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Sao10K/L3-RP-v3.3
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Sao10K/L3-RP-v3.3
model_name: V3-Private-Neph-Custom-1
model_num_parameters: 8030261248.0
model_repo: Sao10K/L3-RP-v3.3
model_size: 8B
num_battles: 14776
num_wins: 7770
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-06-14T17:11:34+00:00
us_pacific_date: 2024-06-14
win_ratio: 0.5258527341635084
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-rp-v3-3-v4-mkmlizer
Waiting for job on sao10k-l3-rp-v3-3-v4-mkmlizer to finish
sao10k-l3-rp-v3-3-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ _____ __ __ ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ /___/ ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ Version: 0.8.14 ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ https://mk1.ai ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ belonging to: ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ Chai Research Corp. ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v3-3-v4-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.
sao10k-l3-rp-v3-3-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
sao10k-l3-rp-v3-3-v4-mkmlizer: Downloaded to shared memory in 31.995s
sao10k-l3-rp-v3-3-v4-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v3-3-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v3-3-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:06, 2.31s/it] Loading 0: 6%|▌ | 18/291 [00:04<00:52, 5.23it/s] Loading 0: 12%|█▏ | 36/291 [00:04<00:20, 12.41it/s] Loading 0: 19%|█▊ | 54/291 [00:04<00:10, 21.68it/s] Loading 0: 24%|██▎ | 69/291 [00:05<00:08, 26.11it/s] Loading 0: 29%|██▉ | 85/291 [00:05<00:05, 36.67it/s] Loading 0: 34%|███▎ | 98/291 [00:05<00:04, 45.58it/s] Loading 0: 38%|███▊ | 112/291 [00:05<00:03, 56.47it/s] Loading 0: 43%|████▎ | 126/291 [00:05<00:02, 68.82it/s] Loading 0: 48%|████▊ | 140/291 [00:05<00:01, 81.15it/s] Loading 0: 54%|█████▍ | 158/291 [00:05<00:01, 98.05it/s] Loading 0: 59%|█████▉ | 172/291 [00:06<00:01, 66.03it/s] Loading 0: 64%|██████▍ | 186/291 [00:06<00:01, 77.91it/s] Loading 0: 70%|███████ | 204/291 [00:06<00:00, 94.62it/s] Loading 0: 76%|███████▋ | 222/291 [00:06<00:00, 108.97it/s] Loading 0: 82%|████████▏ | 239/291 [00:06<00:00, 121.64it/s] Loading 0: 87%|████████▋ | 254/291 [00:06<00:00, 127.47it/s] Loading 0: 92%|█████████▏| 269/291 [00:07<00:00, 75.18it/s] Loading 0: 97%|█████████▋| 283/291 [00:07<00:00, 81.79it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-rp-v3-3-v4-mkmlizer: quantized model in 23.566s
sao10k-l3-rp-v3-3-v4-mkmlizer: Processed model Sao10K/L3-RP-v3.3 in 58.164s
sao10k-l3-rp-v3-3-v4-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v3-3-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v3-3-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v4
sao10k-l3-rp-v3-3-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v4/special_tokens_map.json
sao10k-l3-rp-v3-3-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v4/config.json
sao10k-l3-rp-v3-3-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v4/tokenizer_config.json
sao10k-l3-rp-v3-3-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v4/tokenizer.json
sao10k-l3-rp-v3-3-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v4/flywheel_model.0.safetensors
sao10k-l3-rp-v3-3-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v3-3-v4-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.
sao10k-l3-rp-v3-3-v4-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-3-v4-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.
sao10k-l3-rp-v3-3-v4-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-3-v4-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.
sao10k-l3-rp-v3-3-v4-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-3-v4-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()
sao10k-l3-rp-v3-3-v4-mkmlizer: return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v3-3-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v3-3-v4-mkmlizer: Saving duration: 0.401s
sao10k-l3-rp-v3-3-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.950s
sao10k-l3-rp-v3-3-v4-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v3-3-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v3-3-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v4_reward
sao10k-l3-rp-v3-3-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v4_reward/config.json
sao10k-l3-rp-v3-3-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v4_reward/special_tokens_map.json
sao10k-l3-rp-v3-3-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v4_reward/tokenizer_config.json
sao10k-l3-rp-v3-3-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v4_reward/merges.txt
sao10k-l3-rp-v3-3-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v4_reward/tokenizer.json
sao10k-l3-rp-v3-3-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v4_reward/vocab.json
sao10k-l3-rp-v3-3-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v4_reward/reward.tensors
Job sao10k-l3-rp-v3-3-v4-mkmlizer completed after 94.04s with status: succeeded
Stopping job with name sao10k-l3-rp-v3-3-v4-mkmlizer
Pipeline stage MKMLizer completed in 97.52s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v3-3-v4
Waiting for inference service sao10k-l3-rp-v3-3-v4 to be ready
Inference service sao10k-l3-rp-v3-3-v4 ready after 60.34931969642639s
Pipeline stage ISVCDeployer completed in 67.87s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0845437049865723s
Received healthy response to inference request in 1.2226085662841797s
Received healthy response to inference request in 2.4959282875061035s
Received healthy response to inference request in 1.2569036483764648s
Received healthy response to inference request in 1.2078418731689453s
5 requests
0 failed requests
5th percentile: 1.2107952117919922
10th percentile: 1.2137485504150392
20th percentile: 1.2196552276611328
30th percentile: 1.2294675827026367
40th percentile: 1.2431856155395509
50th percentile: 1.2569036483764648
60th percentile: 1.5879596710205077
70th percentile: 1.9190156936645506
80th percentile: 2.1668206214904786
90th percentile: 2.331374454498291
95th percentile: 2.413651371002197
99th percentile: 2.479472904205322
mean time: 1.6535652160644532
Pipeline stage StressChecker completed in 9.07s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.07s
sao10k-l3-rp-v3-3_v4 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v3-3_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-rp-v3-3_v4
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-rp-v3-3-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.74s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v3-3-v4/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v3-3-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v3-3-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v3-3-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v3-3-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v3-3-v4_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v3-3-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v3-3-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v3-3-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v3-3-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v3-3-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v3-3-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 9.05s
sao10k-l3-rp-v3-3_v4 status is now torndown due to DeploymentManager action