submission_id: hastagaras-ultimatehalu-_1591_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/UltimateHALU-8B-L3-Blackroot
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.85, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 100, '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: 2024-06-01T12:59:34+00:00
model_name: tes
model_eval_status: success
model_group: Hastagaras/UltimateHALU-
num_battles: 9854
num_wins: 5317
celo_rating: 1213.67
safety_score: 0.93
propriety_score: 0.8
propriety_total_count: 5.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: tes
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/UltimateHALU-8B-L3-Blackroot
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.5395778364116095
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-ultimatehalu-1591-v1-mkmlizer
Waiting for job on hastagaras-ultimatehalu-1591-v1-mkmlizer to finish
hastagaras-ultimatehalu-1591-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ /___/ ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ belonging to: ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ║ ║
hastagaras-ultimatehalu-1591-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-ultimatehalu-1591-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-ultimatehalu-1591-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-ultimatehalu-1591-v1-mkmlizer: Downloaded to shared memory in 29.553s
hastagaras-ultimatehalu-1591-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-ultimatehalu-1591-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-ultimatehalu-1591-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:56, 2.27s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.39it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.69it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.04it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.36it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 36.35it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.17it/s] Loading 0: 39%|███▉ | 113/291 [00:05<00:02, 63.91it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:01, 80.79it/s] Loading 0: 51%|█████ | 149/291 [00:05<00:01, 96.96it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 74.94it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 90.62it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 104.60it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 117.54it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 129.22it/s] Loading 0: 87%|████████▋ | 254/291 [00:06<00:00, 136.38it/s] Loading 0: 93%|█████████▎| 270/291 [00:06<00:00, 86.11it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 94.91it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-ultimatehalu-1591-v1-mkmlizer: quantized model in 23.304s
hastagaras-ultimatehalu-1591-v1-mkmlizer: Processed model Hastagaras/UltimateHALU-8B-L3-Blackroot in 55.441s
hastagaras-ultimatehalu-1591-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-ultimatehalu-1591-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-ultimatehalu-1591-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-ultimatehalu-1591-v1
hastagaras-ultimatehalu-1591-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-ultimatehalu-1591-v1/special_tokens_map.json
hastagaras-ultimatehalu-1591-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-ultimatehalu-1591-v1/tokenizer_config.json
hastagaras-ultimatehalu-1591-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-ultimatehalu-1591-v1/config.json
hastagaras-ultimatehalu-1591-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-ultimatehalu-1591-v1/tokenizer.json
hastagaras-ultimatehalu-1591-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-ultimatehalu-1591-v1/flywheel_model.0.safetensors
hastagaras-ultimatehalu-1591-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-ultimatehalu-1591-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-ultimatehalu-1591-v1-mkmlizer: warnings.warn(
hastagaras-ultimatehalu-1591-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-ultimatehalu-1591-v1-mkmlizer: warnings.warn(
hastagaras-ultimatehalu-1591-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-ultimatehalu-1591-v1-mkmlizer: warnings.warn(
hastagaras-ultimatehalu-1591-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-ultimatehalu-1591-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-ultimatehalu-1591-v1-mkmlizer: Saving duration: 0.397s
hastagaras-ultimatehalu-1591-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.468s
hastagaras-ultimatehalu-1591-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-ultimatehalu-1591-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-ultimatehalu-1591-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-ultimatehalu-1591-v1_reward
hastagaras-ultimatehalu-1591-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-ultimatehalu-1591-v1_reward/config.json
hastagaras-ultimatehalu-1591-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-ultimatehalu-1591-v1_reward/special_tokens_map.json
hastagaras-ultimatehalu-1591-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-ultimatehalu-1591-v1_reward/tokenizer_config.json
hastagaras-ultimatehalu-1591-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-ultimatehalu-1591-v1_reward/merges.txt
hastagaras-ultimatehalu-1591-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-ultimatehalu-1591-v1_reward/vocab.json
hastagaras-ultimatehalu-1591-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-ultimatehalu-1591-v1_reward/tokenizer.json
hastagaras-ultimatehalu-1591-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-ultimatehalu-1591-v1_reward/reward.tensors
Job hastagaras-ultimatehalu-1591-v1-mkmlizer completed after 83.13s with status: succeeded
Stopping job with name hastagaras-ultimatehalu-1591-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-ultimatehalu-1591-v1
Waiting for inference service hastagaras-ultimatehalu-1591-v1 to be ready
Inference service hastagaras-ultimatehalu-1591-v1 ready after 40.24555039405823s
Pipeline stage ISVCDeployer completed in 47.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.263214111328125s
Received healthy response to inference request in 1.3384745121002197s
Received healthy response to inference request in 1.3080806732177734s
Received healthy response to inference request in 1.2878448963165283s
Received healthy response to inference request in 1.2462725639343262s
5 requests
0 failed requests
5th percentile: 1.2545870304107667
10th percentile: 1.262901496887207
20th percentile: 1.2795304298400878
30th percentile: 1.2918920516967773
40th percentile: 1.2999863624572754
50th percentile: 1.3080806732177734
60th percentile: 1.320238208770752
70th percentile: 1.3323957443237304
80th percentile: 1.523422431945801
90th percentile: 1.893318271636963
95th percentile: 2.0782661914825438
99th percentile: 2.2262245273590087
mean time: 1.4887773513793945
Pipeline stage StressChecker completed in 8.11s
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-ultimatehalu-_1591_v1 status is now deployed due to DeploymentManager action
hastagaras-ultimatehalu-_1591_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics