submission_id: alsebay-smaid-v0-3_v2
developer_uid: Alsebay
status: inactive
model_repo: Alsebay/SMaid-v0.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.15, 'top_p': 0.5, 'min_p': 0.075, 'top_k': 50, '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: 2024-06-22T22:33:18+00:00
model_name: alsebay-smaid-v0-3_v2
model_group: Alsebay/SMaid-v0.3
num_battles: 15916
num_wins: 7783
celo_rating: 1182.45
propriety_score: 0.7151658146546074
propriety_total_count: 7629.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: alsebay-smaid-v0-3_v2
ineligible_reason: None
language_model: Alsebay/SMaid-v0.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-22
win_ratio: 0.48900477506911283
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alsebay-smaid-v0-3-v2-mkmlizer
Waiting for job on alsebay-smaid-v0-3-v2-mkmlizer to finish
alsebay-smaid-v0-3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alsebay-smaid-v0-3-v2-mkmlizer: ║ _____ __ __ ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ /___/ ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ Version: 0.8.14 ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ https://mk1.ai ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ belonging to: ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ Chai Research Corp. ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alsebay-smaid-v0-3-v2-mkmlizer: ║ ║
alsebay-smaid-v0-3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alsebay-smaid-v0-3-v2-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.
alsebay-smaid-v0-3-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
alsebay-smaid-v0-3-v2-mkmlizer: Downloaded to shared memory in 48.096s
alsebay-smaid-v0-3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
alsebay-smaid-v0-3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alsebay-smaid-v0-3-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:26, 2.38s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:05, 4.19it/s] Loading 0: 8%|▊ | 23/291 [00:05<00:38, 6.93it/s] Loading 0: 14%|█▎ | 40/291 [00:05<00:16, 15.36it/s] Loading 0: 18%|█▊ | 51/291 [00:05<00:11, 21.72it/s] Loading 0: 21%|██ | 61/291 [00:05<00:08, 25.96it/s] Loading 0: 26%|██▋ | 77/291 [00:05<00:05, 39.74it/s] Loading 0: 32%|███▏ | 94/291 [00:05<00:03, 56.33it/s] Loading 0: 37%|███▋ | 107/291 [00:05<00:03, 53.63it/s] Loading 0: 42%|████▏ | 123/291 [00:06<00:02, 68.16it/s] Loading 0: 48%|████▊ | 141/291 [00:06<00:02, 67.19it/s] Loading 0: 55%|█████▍ | 159/291 [00:06<00:01, 83.38it/s] Loading 0: 61%|██████ | 177/291 [00:06<00:01, 98.59it/s] Loading 0: 65%|██████▌ | 190/291 [00:06<00:01, 83.25it/s] Loading 0: 70%|███████ | 204/291 [00:06<00:00, 93.29it/s] Loading 0: 76%|███████▋ | 222/291 [00:07<00:00, 79.29it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:00, 94.64it/s] Loading 0: 88%|████████▊ | 256/291 [00:07<00:00, 109.21it/s] Loading 0: 93%|█████████▎| 270/291 [00:07<00:00, 85.70it/s] Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 96.34it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
alsebay-smaid-v0-3-v2-mkmlizer: quantized model in 21.595s
alsebay-smaid-v0-3-v2-mkmlizer: Processed model Alsebay/SMaid-v0.3 in 70.835s
alsebay-smaid-v0-3-v2-mkmlizer: creating bucket guanaco-mkml-models
alsebay-smaid-v0-3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alsebay-smaid-v0-3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alsebay-smaid-v0-3-v2
alsebay-smaid-v0-3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alsebay-smaid-v0-3-v2/config.json
alsebay-smaid-v0-3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alsebay-smaid-v0-3-v2/special_tokens_map.json
alsebay-smaid-v0-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alsebay-smaid-v0-3-v2/tokenizer_config.json
alsebay-smaid-v0-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alsebay-smaid-v0-3-v2/tokenizer.json
alsebay-smaid-v0-3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
alsebay-smaid-v0-3-v2-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.
alsebay-smaid-v0-3-v2-mkmlizer: warnings.warn(
alsebay-smaid-v0-3-v2-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.
alsebay-smaid-v0-3-v2-mkmlizer: warnings.warn(
alsebay-smaid-v0-3-v2-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.
alsebay-smaid-v0-3-v2-mkmlizer: warnings.warn(
alsebay-smaid-v0-3-v2-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()
alsebay-smaid-v0-3-v2-mkmlizer: return self.fget.__get__(instance, owner)()
alsebay-smaid-v0-3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alsebay-smaid-v0-3-v2-mkmlizer: Saving duration: 0.347s
alsebay-smaid-v0-3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.416s
alsebay-smaid-v0-3-v2-mkmlizer: creating bucket guanaco-reward-models
alsebay-smaid-v0-3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alsebay-smaid-v0-3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alsebay-smaid-v0-3-v2_reward
alsebay-smaid-v0-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alsebay-smaid-v0-3-v2_reward/tokenizer_config.json
alsebay-smaid-v0-3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alsebay-smaid-v0-3-v2_reward/special_tokens_map.json
alsebay-smaid-v0-3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alsebay-smaid-v0-3-v2_reward/config.json
alsebay-smaid-v0-3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alsebay-smaid-v0-3-v2_reward/merges.txt
alsebay-smaid-v0-3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alsebay-smaid-v0-3-v2_reward/vocab.json
Job alsebay-smaid-v0-3-v2-mkmlizer completed after 105.27s with status: succeeded
Stopping job with name alsebay-smaid-v0-3-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.36s
Running pipeline stage ISVCDeployer
Creating inference service alsebay-smaid-v0-3-v2
Waiting for inference service alsebay-smaid-v0-3-v2 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service alsebay-smaid-v0-3-v2 ready after 40.20721077919006s
Pipeline stage ISVCDeployer completed in 45.91s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.041445255279541s
Received healthy response to inference request in 1.1234958171844482s
Received healthy response to inference request in 1.1366825103759766s
Received healthy response to inference request in 1.1045610904693604s
Received healthy response to inference request in 1.128504991531372s
5 requests
0 failed requests
5th percentile: 1.1083480358123778
10th percentile: 1.1121349811553956
20th percentile: 1.1197088718414308
30th percentile: 1.124497652053833
40th percentile: 1.1265013217926025
50th percentile: 1.128504991531372
60th percentile: 1.1317759990692138
70th percentile: 1.1350470066070557
80th percentile: 1.3176350593566897
90th percentile: 1.6795401573181152
95th percentile: 1.860492706298828
99th percentile: 2.0052547454833984
mean time: 1.3069379329681396
Pipeline stage StressChecker completed in 7.32s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
alsebay-smaid-v0-3_v2 status is now deployed due to DeploymentManager action
alsebay-smaid-v0-3_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics