submission_id: sao10k-l3-rp-v3-2_v5
developer_uid: sao10k
status: inactive
model_repo: Sao10K/L3-RP-v3.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.12, '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': 512, 'best_of': 16, 'max_output_tokens': 64}
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}
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: 2024-06-14T17:10:46+00:00
model_name: V3-Stheno-v3-2-Alpha
model_eval_status: success
model_group: Sao10K/L3-RP-v3.2
num_battles: 17042
num_wins: 9117
celo_rating: 1217.32
propriety_score: 0.689729867482161
propriety_total_count: 7848.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: V3-Stheno-v3-2-Alpha
ineligible_reason: None
language_model: Sao10K/L3-RP-v3.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-14
win_ratio: 0.5349724210773383
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-rp-v3-2-v5-mkmlizer
Waiting for job on sao10k-l3-rp-v3-2-v5-mkmlizer to finish
sao10k-l3-rp-v3-2-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ _____ __ __ ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ /___/ ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ Version: 0.8.14 ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ https://mk1.ai ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ belonging to: ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ Chai Research Corp. ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ║ ║
sao10k-l3-rp-v3-2-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v3-2-v5-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-v3-2-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
sao10k-l3-rp-v3-2-v5-mkmlizer: Downloaded to shared memory in 34.961s
sao10k-l3-rp-v3-2-v5-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v3-2-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v3-2-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:53, 2.26s/it] Loading 0: 5%|▌ | 16/291 [00:04<00:58, 4.72it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.62it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.03it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.48it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.92it/s] Loading 0: 31%|███ | 90/291 [00:05<00:04, 42.87it/s] Loading 0: 36%|███▌ | 104/291 [00:05<00:03, 55.17it/s] Loading 0: 42%|████▏ | 121/291 [00:05<00:02, 72.62it/s] Loading 0: 48%|████▊ | 139/291 [00:05<00:01, 89.90it/s] Loading 0: 53%|█████▎ | 154/291 [00:05<00:01, 97.94it/s] Loading 0: 58%|█████▊ | 168/291 [00:06<00:01, 68.18it/s] Loading 0: 64%|██████▍ | 186/291 [00:06<00:01, 86.07it/s] Loading 0: 70%|███████ | 204/291 [00:06<00:00, 102.71it/s] Loading 0: 76%|███████▋ | 222/291 [00:06<00:00, 117.75it/s] Loading 0: 82%|████████▏ | 240/291 [00:06<00:00, 131.19it/s] Loading 0: 89%|████████▊ | 258/291 [00:06<00:00, 141.94it/s] Loading 0: 95%|█████████▍| 275/291 [00:07<00:00, 93.89it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-rp-v3-2-v5-mkmlizer: quantized model in 23.063s
sao10k-l3-rp-v3-2-v5-mkmlizer: Processed model Sao10K/L3-RP-v3.2 in 60.534s
sao10k-l3-rp-v3-2-v5-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v3-2-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v3-2-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v3-2-v5
sao10k-l3-rp-v3-2-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-2-v5/tokenizer_config.json
sao10k-l3-rp-v3-2-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-2-v5/config.json
sao10k-l3-rp-v3-2-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-2-v5/special_tokens_map.json
sao10k-l3-rp-v3-2-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-2-v5/tokenizer.json
sao10k-l3-rp-v3-2-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v3-2-v5-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-v3-2-v5-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-2-v5-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-v3-2-v5-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-2-v5-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-v3-2-v5-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-2-v5-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-v3-2-v5-mkmlizer: return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v3-2-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v3-2-v5-mkmlizer: Saving duration: 0.406s
sao10k-l3-rp-v3-2-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.785s
sao10k-l3-rp-v3-2-v5-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v3-2-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v3-2-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v3-2-v5_reward
sao10k-l3-rp-v3-2-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v3-2-v5_reward/merges.txt
sao10k-l3-rp-v3-2-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v3-2-v5_reward/config.json
sao10k-l3-rp-v3-2-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v3-2-v5_reward/special_tokens_map.json
sao10k-l3-rp-v3-2-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v3-2-v5_reward/tokenizer_config.json
sao10k-l3-rp-v3-2-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v3-2-v5_reward/vocab.json
sao10k-l3-rp-v3-2-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v3-2-v5_reward/tokenizer.json
Job sao10k-l3-rp-v3-2-v5-mkmlizer completed after 93.83s with status: succeeded
Stopping job with name sao10k-l3-rp-v3-2-v5-mkmlizer
Pipeline stage MKMLizer completed in 97.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v3-2-v5
Waiting for inference service sao10k-l3-rp-v3-2-v5 to be ready
Inference service sao10k-l3-rp-v3-2-v5 ready after 40.50527739524841s
Pipeline stage ISVCDeployer completed in 47.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.137777328491211s
Received healthy response to inference request in 1.3170275688171387s
Received healthy response to inference request in 1.3146798610687256s
Received healthy response to inference request in 1.2889816761016846s
Received healthy response to inference request in 1.3535163402557373s
5 requests
0 failed requests
5th percentile: 1.2941213130950928
10th percentile: 1.299260950088501
20th percentile: 1.3095402240753173
30th percentile: 1.3151494026184083
40th percentile: 1.3160884857177735
50th percentile: 1.3170275688171387
60th percentile: 1.3316230773925781
70th percentile: 1.3462185859680176
80th percentile: 1.5103685379028322
90th percentile: 1.8240729331970216
95th percentile: 1.980925130844116
99th percentile: 2.106406888961792
mean time: 1.4823965549468994
Pipeline stage StressChecker completed in 8.17s
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 0.06s
sao10k-l3-rp-v3-2_v5 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v3-2_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics