submission_id: sao10k-l3-rp-v4-1_v3
developer_uid: sao10k
status: inactive
model_repo: Sao10K/L3-RP-v4.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 100, '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: 2024-06-10T17:51:34+00:00
model_name: V4-Expr1-Beta
model_eval_status: success
model_group: Sao10K/L3-RP-v4.1
num_battles: 6512
num_wins: 3558
celo_rating: 1218.91
safety_score: 0.9
propriety_score: 0.6702981651376146
propriety_total_count: 1744.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: V4-Expr1-Beta
ineligible_reason: propriety_total_count < 5000
language_model: Sao10K/L3-RP-v4.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-10
win_ratio: 0.5463759213759214
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-rp-v4-1-v3-mkmlizer
Waiting for job on sao10k-l3-rp-v4-1-v3-mkmlizer to finish
sao10k-l3-rp-v4-1-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ _____ __ __ ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ /___/ ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ Version: 0.8.14 ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ https://mk1.ai ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ belonging to: ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ Chai Research Corp. ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ║ ║
sao10k-l3-rp-v4-1-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v4-1-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.
sao10k-l3-rp-v4-1-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
sao10k-l3-rp-v4-1-v3-mkmlizer: Downloaded to shared memory in 14.885s
sao10k-l3-rp-v4-1-v3-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v4-1-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v4-1-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:03<09:27, 1.96s/it] Loading 0: 8%|▊ | 22/291 [00:04<00:35, 7.50it/s] Loading 0: 14%|█▍ | 42/291 [00:04<00:14, 16.61it/s] Loading 0: 21%|██ | 60/291 [00:04<00:10, 23.05it/s] Loading 0: 29%|██▉ | 85/291 [00:04<00:05, 39.19it/s] Loading 0: 36%|███▌ | 105/291 [00:04<00:03, 53.62it/s] Loading 0: 45%|████▍ | 130/291 [00:04<00:02, 75.87it/s] Loading 0: 52%|█████▏ | 150/291 [00:04<00:01, 92.22it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:01, 77.46it/s] Loading 0: 66%|██████▋ | 193/291 [00:05<00:00, 100.04it/s] Loading 0: 73%|███████▎ | 213/291 [00:05<00:00, 115.19it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:00, 139.43it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 148.97it/s] Loading 0: 95%|█████████▌| 277/291 [00:06<00:00, 103.53it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-rp-v4-1-v3-mkmlizer: quantized model in 16.512s
sao10k-l3-rp-v4-1-v3-mkmlizer: Processed model Sao10K/L3-RP-v4.1 in 32.341s
sao10k-l3-rp-v4-1-v3-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v4-1-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v4-1-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v4-1-v3
sao10k-l3-rp-v4-1-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v4-1-v3/special_tokens_map.json
sao10k-l3-rp-v4-1-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v4-1-v3/config.json
sao10k-l3-rp-v4-1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v4-1-v3/tokenizer_config.json
sao10k-l3-rp-v4-1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v4-1-v3/tokenizer.json
sao10k-l3-rp-v4-1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v4-1-v3/flywheel_model.0.safetensors
sao10k-l3-rp-v4-1-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v4-1-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.
sao10k-l3-rp-v4-1-v3-mkmlizer: warnings.warn(
sao10k-l3-rp-v4-1-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.
sao10k-l3-rp-v4-1-v3-mkmlizer: warnings.warn(
sao10k-l3-rp-v4-1-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.
sao10k-l3-rp-v4-1-v3-mkmlizer: warnings.warn(
sao10k-l3-rp-v4-1-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()
sao10k-l3-rp-v4-1-v3-mkmlizer: return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v4-1-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v4-1-v3-mkmlizer: Saving duration: 0.254s
sao10k-l3-rp-v4-1-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.015s
sao10k-l3-rp-v4-1-v3-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v4-1-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v4-1-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v4-1-v3_reward
sao10k-l3-rp-v4-1-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v4-1-v3_reward/config.json
sao10k-l3-rp-v4-1-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v4-1-v3_reward/special_tokens_map.json
sao10k-l3-rp-v4-1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v4-1-v3_reward/tokenizer_config.json
sao10k-l3-rp-v4-1-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v4-1-v3_reward/merges.txt
sao10k-l3-rp-v4-1-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v4-1-v3_reward/vocab.json
sao10k-l3-rp-v4-1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v4-1-v3_reward/tokenizer.json
sao10k-l3-rp-v4-1-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v4-1-v3_reward/reward.tensors
Job sao10k-l3-rp-v4-1-v3-mkmlizer completed after 65.04s with status: succeeded
Stopping job with name sao10k-l3-rp-v4-1-v3-mkmlizer
Pipeline stage MKMLizer completed in 69.67s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v4-1-v3
Waiting for inference service sao10k-l3-rp-v4-1-v3 to be ready
Inference service sao10k-l3-rp-v4-1-v3 ready after 110.63460564613342s
Pipeline stage ISVCDeployer completed in 118.55s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.160653829574585s
Received healthy response to inference request in 1.351708173751831s
Received healthy response to inference request in 19.09886336326599s
Received healthy response to inference request in 4.21252965927124s
Received healthy response to inference request in 1.3463683128356934s
5 requests
0 failed requests
5th percentile: 1.347436285018921
10th percentile: 1.3485042572021484
20th percentile: 1.3506402015686034
30th percentile: 1.5134973049163818
40th percentile: 1.8370755672454835
50th percentile: 2.160653829574585
60th percentile: 2.9814041614532467
70th percentile: 3.802154493331909
80th percentile: 7.189796400070193
90th percentile: 13.144329881668092
95th percentile: 16.121596622467038
99th percentile: 18.5034100151062
mean time: 5.634024667739868
Pipeline stage StressChecker completed in 28.83s
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
sao10k-l3-rp-v4-1_v3 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v4-1_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics