submission_id: hastagaras-aelah-8b-llam_5487_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Aelah-8B-Llama3-TEST
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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: 2024-05-25T22:56:59+00:00
model_name: etdah
model_eval_status: success
model_group: Hastagaras/Aelah-8B-Llam
num_battles: 11908
num_wins: 6269
celo_rating: 1195.94
safety_score: 0.98
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: etdah
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Aelah-8B-Llama3-TEST
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-25
win_ratio: 0.5264528048370843
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-aelah-8b-llam-5487-v1-mkmlizer
Waiting for job on hastagaras-aelah-8b-llam-5487-v1-mkmlizer to finish
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ /___/ ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ belonging to: ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ║ ║
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-aelah-8b-llam-5487-v1-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-aelah-8b-llam-5487-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: Downloaded to shared memory in 33.467s
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 129.01it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 150.73it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 157.46it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 161.71it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 72.74it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 80.78it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 98.74it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 113.60it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 126.78it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 137.50it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 93.62it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 101.39it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 112.44it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 122.09it/s] Loading 0: 86%|████████▋ | 251/291 [00:02<00:00, 125.57it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 129.97it/s] Loading 0: 98%|█████████▊| 284/291 [00:02<00:00, 142.57it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: quantized model in 22.890s
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: Processed model Hastagaras/Aelah-8B-Llama3-TEST in 58.929s
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v1
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v1/tokenizer_config.json
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v1/special_tokens_map.json
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v1/tokenizer.json
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v1/config.json
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-aelah-8b-llam-5487-v1/flywheel_model.0.safetensors
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-aelah-8b-llam-5487-v1-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-aelah-8b-llam-5487-v1-mkmlizer: warnings.warn(
hastagaras-aelah-8b-llam-5487-v1-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-aelah-8b-llam-5487-v1-mkmlizer: warnings.warn(
hastagaras-aelah-8b-llam-5487-v1-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-aelah-8b-llam-5487-v1-mkmlizer: warnings.warn(
hastagaras-aelah-8b-llam-5487-v1-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-aelah-8b-llam-5487-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: Saving duration: 0.430s
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.575s
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v1_reward
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v1_reward/config.json
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v1_reward/special_tokens_map.json
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v1_reward/vocab.json
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v1_reward/merges.txt
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v1_reward/tokenizer.json
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v1_reward/tokenizer_config.json
hastagaras-aelah-8b-llam-5487-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-aelah-8b-llam-5487-v1_reward/reward.tensors
Job hastagaras-aelah-8b-llam-5487-v1-mkmlizer completed after 82.94s with status: succeeded
Stopping job with name hastagaras-aelah-8b-llam-5487-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.92s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-aelah-8b-llam-5487-v1
Waiting for inference service hastagaras-aelah-8b-llam-5487-v1 to be ready
Inference service hastagaras-aelah-8b-llam-5487-v1 ready after 50.268773794174194s
Pipeline stage ISVCDeployer completed in 58.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2505335807800293s
Received healthy response to inference request in 1.354121446609497s
Received healthy response to inference request in 1.3107757568359375s
Received healthy response to inference request in 1.2828867435455322s
Received healthy response to inference request in 1.2313292026519775s
5 requests
0 failed requests
5th percentile: 1.2416407108306884
10th percentile: 1.2519522190093995
20th percentile: 1.2725752353668214
30th percentile: 1.2884645462036133
40th percentile: 1.2996201515197754
50th percentile: 1.3107757568359375
60th percentile: 1.3281140327453613
70th percentile: 1.3454523086547852
80th percentile: 1.5334038734436037
90th percentile: 1.8919687271118164
95th percentile: 2.071251153945923
99th percentile: 2.214677095413208
mean time: 1.4859293460845948
Pipeline stage StressChecker completed in 8.00s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-aelah-8b-llam_5487_v1 status is now deployed due to DeploymentManager action
hastagaras-aelah-8b-llam_5487_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics