submission_id: alsebay-smaid-v0-3_v3
developer_uid: Alsebay
status: inactive
model_repo: Alsebay/SMaid-v0.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, '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: 2024-06-22T23:45:55+00:00
model_name: alsebay-smaid-v0-3_v1
model_group: Alsebay/SMaid-v0.3
num_battles: 30438
num_wins: 15887
celo_rating: 1201.31
propriety_score: 0.7074949169178995
propriety_total_count: 14263.0
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_v1
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: 0.5219462513962809
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alsebay-smaid-v0-3-v3-mkmlizer
Waiting for job on alsebay-smaid-v0-3-v3-mkmlizer to finish
alsebay-smaid-v0-3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alsebay-smaid-v0-3-v3-mkmlizer: ║ _____ __ __ ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ /___/ ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ Version: 0.8.14 ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ https://mk1.ai ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ The license key for the current software has been verified as ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ belonging to: ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ Chai Research Corp. ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alsebay-smaid-v0-3-v3-mkmlizer: ║ ║
alsebay-smaid-v0-3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alsebay-smaid-v0-3-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.
alsebay-smaid-v0-3-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
alsebay-smaid-v0-3-v3-mkmlizer: Downloaded to shared memory in 21.536s
alsebay-smaid-v0-3-v3-mkmlizer: quantizing model to /dev/shm/model_cache
alsebay-smaid-v0-3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alsebay-smaid-v0-3-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:27, 2.38s/it] Loading 0: 5%|▍ | 14/291 [00:04<01:10, 3.90it/s] Loading 0: 8%|▊ | 22/291 [00:05<00:40, 6.65it/s] Loading 0: 12%|█▏ | 34/291 [00:05<00:20, 12.51it/s] Loading 0: 17%|█▋ | 50/291 [00:05<00:10, 22.48it/s] Loading 0: 21%|██ | 61/291 [00:05<00:08, 26.67it/s] Loading 0: 26%|██▋ | 77/291 [00:05<00:05, 39.61it/s] Loading 0: 32%|███▏ | 94/291 [00:05<00:03, 54.93it/s] Loading 0: 36%|███▋ | 106/291 [00:06<00:03, 52.03it/s] Loading 0: 42%|████▏ | 122/291 [00:06<00:02, 66.66it/s] Loading 0: 48%|████▊ | 139/291 [00:06<00:01, 82.61it/s] Loading 0: 52%|█████▏ | 152/291 [00:06<00:01, 69.99it/s] Loading 0: 57%|█████▋ | 167/291 [00:06<00:01, 82.37it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 74.26it/s] Loading 0: 67%|██████▋ | 196/291 [00:06<00:01, 82.12it/s] Loading 0: 73%|███████▎ | 212/291 [00:07<00:00, 95.54it/s] Loading 0: 77%|███████▋ | 224/291 [00:07<00:00, 78.30it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:00, 90.53it/s] Loading 0: 88%|████████▊ | 256/291 [00:07<00:00, 104.65it/s] Loading 0: 92%|█████████▏| 269/291 [00:07<00:00, 80.58it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 92.10it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
alsebay-smaid-v0-3-v3-mkmlizer: quantized model in 19.278s
alsebay-smaid-v0-3-v3-mkmlizer: Processed model Alsebay/SMaid-v0.3 in 41.932s
alsebay-smaid-v0-3-v3-mkmlizer: creating bucket guanaco-mkml-models
alsebay-smaid-v0-3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alsebay-smaid-v0-3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alsebay-smaid-v0-3-v3
alsebay-smaid-v0-3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alsebay-smaid-v0-3-v3/config.json
alsebay-smaid-v0-3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alsebay-smaid-v0-3-v3/special_tokens_map.json
alsebay-smaid-v0-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alsebay-smaid-v0-3-v3/tokenizer_config.json
alsebay-smaid-v0-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alsebay-smaid-v0-3-v3/tokenizer.json
alsebay-smaid-v0-3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alsebay-smaid-v0-3-v3/flywheel_model.0.safetensors
alsebay-smaid-v0-3-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
alsebay-smaid-v0-3-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.
alsebay-smaid-v0-3-v3-mkmlizer: warnings.warn(
alsebay-smaid-v0-3-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.
alsebay-smaid-v0-3-v3-mkmlizer: warnings.warn(
alsebay-smaid-v0-3-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()
alsebay-smaid-v0-3-v3-mkmlizer: return self.fget.__get__(instance, owner)()
alsebay-smaid-v0-3-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alsebay-smaid-v0-3-v3-mkmlizer: Saving duration: 0.249s
alsebay-smaid-v0-3-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.342s
alsebay-smaid-v0-3-v3-mkmlizer: creating bucket guanaco-reward-models
alsebay-smaid-v0-3-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alsebay-smaid-v0-3-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alsebay-smaid-v0-3-v3_reward
alsebay-smaid-v0-3-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alsebay-smaid-v0-3-v3_reward/config.json
alsebay-smaid-v0-3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alsebay-smaid-v0-3-v3_reward/tokenizer_config.json
alsebay-smaid-v0-3-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alsebay-smaid-v0-3-v3_reward/special_tokens_map.json
alsebay-smaid-v0-3-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alsebay-smaid-v0-3-v3_reward/vocab.json
alsebay-smaid-v0-3-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alsebay-smaid-v0-3-v3_reward/merges.txt
alsebay-smaid-v0-3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/alsebay-smaid-v0-3-v3_reward/tokenizer.json
alsebay-smaid-v0-3-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/alsebay-smaid-v0-3-v3_reward/reward.tensors
Job alsebay-smaid-v0-3-v3-mkmlizer completed after 62.76s with status: succeeded
Stopping job with name alsebay-smaid-v0-3-v3-mkmlizer
Pipeline stage MKMLizer completed in 63.12s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service alsebay-smaid-v0-3-v3
Waiting for inference service alsebay-smaid-v0-3-v3 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service alsebay-smaid-v0-3-v3 ready after 30.150516510009766s
Pipeline stage ISVCDeployer completed in 35.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9185445308685303s
Received healthy response to inference request in 1.1213860511779785s
Received healthy response to inference request in 1.1324923038482666s
Received healthy response to inference request in 1.1133882999420166s
Received healthy response to inference request in 0.8838047981262207s
5 requests
0 failed requests
5th percentile: 0.9297214984893799
10th percentile: 0.9756381988525391
20th percentile: 1.0674715995788575
30th percentile: 1.114987850189209
40th percentile: 1.1181869506835938
50th percentile: 1.1213860511779785
60th percentile: 1.1258285522460938
70th percentile: 1.130271053314209
80th percentile: 1.2897027492523194
90th percentile: 1.6041236400604248
95th percentile: 1.7613340854644775
99th percentile: 1.8871024417877198
mean time: 1.2339231967926025
Pipeline stage StressChecker completed in 6.89s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
alsebay-smaid-v0-3_v3 status is now deployed due to DeploymentManager action
alsebay-smaid-v0-3_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics