submission_id: hastagaras-yaelah-8b-lla_4014_v3
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Yaelah-8B-Llama3-Test
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|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: 2024-06-02T13:31:06+00:00
model_name: another-test
model_eval_status: success
model_group: Hastagaras/Yaelah-8B-Lla
num_battles: 10716
num_wins: 5891
celo_rating: 1202.74
safety_score: 0.96
propriety_score: 0.6890756302521008
propriety_total_count: 238.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: another-test
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Yaelah-8B-Llama3-Test
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-02
win_ratio: 0.549738708473311
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-yaelah-8b-lla-4014-v3-mkmlizer
Waiting for job on hastagaras-yaelah-8b-lla-4014-v3-mkmlizer to finish
Stopping job with name hastagaras-yaelah-8b-lla-4014-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-yaelah-8b-lla-4014-v3-mkmlizer
Waiting for job on hastagaras-yaelah-8b-lla-4014-v3-mkmlizer to finish
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ /___/ ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ belonging to: ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ║ ║
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-yaelah-8b-lla-4014-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.
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: Downloaded to shared memory in 17.661s
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 122.44it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 150.83it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 160.52it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 161.86it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 85.28it/s] Loading 0: 34%|███▎ | 98/291 [00:00<00:02, 96.38it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:01, 104.82it/s] Loading 0: 43%|████▎ | 125/291 [00:01<00:01, 108.54it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 115.22it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 125.73it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 132.26it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 83.26it/s] Loading 0: 68%|██████▊ | 199/291 [00:01<00:01, 87.67it/s] Loading 0: 74%|███████▎ | 214/291 [00:01<00:00, 100.56it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 111.63it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 123.99it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 133.03it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 139.61it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: quantized model in 24.203s
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: Processed model Hastagaras/Yaelah-8B-Llama3-Test in 44.500s
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v3
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v3/config.json
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v3/tokenizer_config.json
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v3/special_tokens_map.json
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v3/tokenizer.json
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-yaelah-8b-lla-4014-v3/flywheel_model.0.safetensors
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-yaelah-8b-lla-4014-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.
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: warnings.warn(
hastagaras-yaelah-8b-lla-4014-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.
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: warnings.warn(
hastagaras-yaelah-8b-lla-4014-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.
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: warnings.warn(
hastagaras-yaelah-8b-lla-4014-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()
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: Saving duration: 0.416s
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.762s
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v3_reward
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v3_reward/config.json
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v3_reward/special_tokens_map.json
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v3_reward/tokenizer_config.json
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v3_reward/merges.txt
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v3_reward/vocab.json
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v3_reward/tokenizer.json
hastagaras-yaelah-8b-lla-4014-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-yaelah-8b-lla-4014-v3_reward/reward.tensors
Job hastagaras-yaelah-8b-lla-4014-v3-mkmlizer completed after 72.97s with status: succeeded
Stopping job with name hastagaras-yaelah-8b-lla-4014-v3-mkmlizer
Pipeline stage MKMLizer completed in 76.39s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-yaelah-8b-lla-4014-v3
Waiting for inference service hastagaras-yaelah-8b-lla-4014-v3 to be ready
Inference service hastagaras-yaelah-8b-lla-4014-v3 ready after 361.9272255897522s
Pipeline stage ISVCDeployer completed in 368.92s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.206636428833008s
Received healthy response to inference request in 1.363354206085205s
Received healthy response to inference request in 1.328620195388794s
%s, retrying in %s seconds...
Received healthy response to inference request in 1.2631237506866455s
Received healthy response to inference request in 1.3581249713897705s
Received healthy response to inference request in 1.3287148475646973s
Received healthy response to inference request in 1.3090760707855225s
Received healthy response to inference request in 1.2471020221710205s
5 requests
0 failed requests
5th percentile: 1.2503063678741455
10th percentile: 1.2535107135772705
20th percentile: 1.2599194049835205
30th percentile: 1.2723142147064208
40th percentile: 1.2906951427459716
50th percentile: 1.3090760707855225
60th percentile: 1.3169315814971925
70th percentile: 1.3247870922088623
80th percentile: 1.334596872329712
90th percentile: 1.3463609218597412
95th percentile: 1.3522429466247559
99th percentile: 1.3569485664367675
mean time: 1.3012283325195313
Pipeline stage StressChecker completed in 17.23s
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
hastagaras-yaelah-8b-lla_4014_v3 status is now deployed due to DeploymentManager action
hastagaras-yaelah-8b-lla_4014_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics