submission_id: sao10k-l3-rp-v3-3_v3
developer_uid: sao10k
status: inactive
model_repo: Sao10K/L3-RP-v3.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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}
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: 2024-06-05T16:21:03+00:00
model_name: V3-Expr2-Delta
model_eval_status: pending
model_group: Sao10K/L3-RP-v3.3
num_battles: 18755
num_wins: 10625
celo_rating: 1220.7
safety_score: None
propriety_score: 0.6804260985352862
propriety_total_count: 751.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: V3-Expr2-Delta
ineligible_reason: propriety_total_count < 5000
language_model: Sao10K/L3-RP-v3.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-05
win_ratio: 0.566515595841109
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-rp-v3-3-v3-mkmlizer
Waiting for job on sao10k-l3-rp-v3-3-v3-mkmlizer to finish
sao10k-l3-rp-v3-3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ _____ __ __ ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ /___/ ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ Version: 0.8.14 ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ https://mk1.ai ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ belonging to: ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ Chai Research Corp. ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ║ ║
sao10k-l3-rp-v3-3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v3-3-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-v3-3-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
sao10k-l3-rp-v3-3-v3-mkmlizer: Downloaded to shared memory in 29.324s
sao10k-l3-rp-v3-3-v3-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v3-3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v3-3-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:41, 2.01s/it] Loading 0: 5%|▌ | 16/291 [00:04<00:52, 5.28it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:19, 12.93it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:10, 23.22it/s] Loading 0: 22%|██▏ | 65/291 [00:04<00:08, 27.52it/s] Loading 0: 28%|██▊ | 81/291 [00:04<00:05, 39.18it/s] Loading 0: 33%|███▎ | 96/291 [00:04<00:03, 51.56it/s] Loading 0: 39%|███▉ | 114/291 [00:04<00:02, 68.61it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 85.91it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 102.13it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 74.97it/s] Loading 0: 63%|██████▎ | 182/291 [00:05<00:01, 88.80it/s] Loading 0: 67%|██████▋ | 196/291 [00:05<00:00, 97.86it/s] Loading 0: 73%|███████▎ | 213/291 [00:05<00:00, 110.19it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:00, 122.81it/s] Loading 0: 86%|████████▌ | 249/291 [00:06<00:00, 132.79it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 85.44it/s] Loading 0: 97%|█████████▋| 283/291 [00:06<00:00, 100.30it/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-v3-mkmlizer: quantized model in 18.232s
sao10k-l3-rp-v3-3-v3-mkmlizer: Processed model Sao10K/L3-RP-v3.3 in 48.500s
sao10k-l3-rp-v3-3-v3-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v3-3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v3-3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v3
sao10k-l3-rp-v3-3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v3/config.json
sao10k-l3-rp-v3-3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v3/special_tokens_map.json
sao10k-l3-rp-v3-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v3/tokenizer_config.json
sao10k-l3-rp-v3-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v3/tokenizer.json
sao10k-l3-rp-v3-3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v3-3-v3/flywheel_model.0.safetensors
sao10k-l3-rp-v3-3-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v3-3-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-v3-3-v3-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-3-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-v3-3-v3-mkmlizer: warnings.warn(
sao10k-l3-rp-v3-3-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-v3-3-v3-mkmlizer: return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v3-3-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v3-3-v3-mkmlizer: Saving duration: 0.279s
sao10k-l3-rp-v3-3-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.176s
sao10k-l3-rp-v3-3-v3-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v3-3-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v3-3-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v3_reward
sao10k-l3-rp-v3-3-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v3_reward/special_tokens_map.json
sao10k-l3-rp-v3-3-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v3_reward/config.json
sao10k-l3-rp-v3-3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v3_reward/tokenizer_config.json
sao10k-l3-rp-v3-3-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v3_reward/merges.txt
sao10k-l3-rp-v3-3-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v3_reward/vocab.json
sao10k-l3-rp-v3-3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v3_reward/tokenizer.json
sao10k-l3-rp-v3-3-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v3-3-v3_reward/reward.tensors
Job sao10k-l3-rp-v3-3-v3-mkmlizer completed after 85.4s with status: succeeded
Stopping job with name sao10k-l3-rp-v3-3-v3-mkmlizer
Pipeline stage MKMLizer completed in 86.38s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v3-3-v3
Waiting for inference service sao10k-l3-rp-v3-3-v3 to be ready
Inference service sao10k-l3-rp-v3-3-v3 ready after 172.18630146980286s
Pipeline stage ISVCDeployer completed in 178.06s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.127324342727661s
Received healthy response to inference request in 1.2114112377166748s
Received healthy response to inference request in 1.2427916526794434s
Received healthy response to inference request in 1.2439358234405518s
Received healthy response to inference request in 1.222557544708252s
5 requests
0 failed requests
5th percentile: 1.2136404991149903
10th percentile: 1.2158697605133058
20th percentile: 1.2203282833099365
30th percentile: 1.2266043663024901
40th percentile: 1.2346980094909668
50th percentile: 1.2427916526794434
60th percentile: 1.2432493209838866
70th percentile: 1.2437069892883301
80th percentile: 1.4206135272979739
90th percentile: 1.7739689350128174
95th percentile: 1.950646638870239
99th percentile: 2.0919888019561768
mean time: 1.4096041202545166
Pipeline stage StressChecker completed in 7.70s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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-v3-3_v3 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v3-3_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics