submission_id: hastagaras-halu-8b-llama_4027_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/HALU-8B-LLAMA3-EXP-6
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.1, 'top_p': 0.95, 'min_p': 0.1, '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: 2024-06-01T06:12:57+00:00
model_name: weird-and-strange2
model_eval_status: success
model_group: Hastagaras/HALU-8B-LLAMA
num_battles: 10298
num_wins: 5605
celo_rating: 1210.02
safety_score: 0.97
propriety_score: 1.0
propriety_total_count: 3.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: weird-and-strange2
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/HALU-8B-LLAMA3-EXP-6
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-31
win_ratio: 0.544280442804428
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-4027-v2-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-4027-v2-mkmlizer to finish
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ║ ║
hastagaras-halu-8b-llama-4027-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-4027-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.
hastagaras-halu-8b-llama-4027-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-4027-v2-mkmlizer: Downloaded to shared memory in 18.487s
hastagaras-halu-8b-llama-4027-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-4027-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-4027-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:55, 2.27s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.39it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.67it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.98it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.39it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 34.01it/s] Loading 0: 33%|███▎ | 95/291 [00:05<00:04, 48.33it/s] Loading 0: 38%|███▊ | 112/291 [00:05<00:02, 64.25it/s] Loading 0: 45%|████▍ | 130/291 [00:05<00:01, 81.15it/s] Loading 0: 50%|█████ | 146/291 [00:05<00:01, 95.36it/s] Loading 0: 56%|█████▌ | 162/291 [00:05<00:01, 106.50it/s] Loading 0: 61%|██████ | 178/291 [00:06<00:01, 75.36it/s] Loading 0: 67%|██████▋ | 195/291 [00:06<00:01, 89.92it/s] Loading 0: 73%|███████▎ | 213/291 [00:06<00:00, 105.54it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:00, 119.46it/s] Loading 0: 86%|████████▌ | 249/291 [00:06<00:00, 130.39it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 89.46it/s] Loading 0: 97%|█████████▋| 283/291 [00:07<00:00, 101.84it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-4027-v2-mkmlizer: quantized model in 24.148s
hastagaras-halu-8b-llama-4027-v2-mkmlizer: Processed model Hastagaras/HALU-8B-LLAMA3-EXP-6 in 45.182s
hastagaras-halu-8b-llama-4027-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-4027-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-4027-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4027-v2
hastagaras-halu-8b-llama-4027-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4027-v2/tokenizer_config.json
hastagaras-halu-8b-llama-4027-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4027-v2/config.json
hastagaras-halu-8b-llama-4027-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4027-v2/special_tokens_map.json
hastagaras-halu-8b-llama-4027-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4027-v2/tokenizer.json
hastagaras-halu-8b-llama-4027-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4027-v2/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-4027-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-4027-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.
hastagaras-halu-8b-llama-4027-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-4027-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.
hastagaras-halu-8b-llama-4027-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-4027-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.
hastagaras-halu-8b-llama-4027-v2-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama-4027-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()
hastagaras-halu-8b-llama-4027-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-4027-v2-mkmlizer: Saving duration: 0.412s
hastagaras-halu-8b-llama-4027-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.232s
hastagaras-halu-8b-llama-4027-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-4027-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-4027-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v2_reward
hastagaras-halu-8b-llama-4027-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v2_reward/tokenizer_config.json
hastagaras-halu-8b-llama-4027-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v2_reward/merges.txt
hastagaras-halu-8b-llama-4027-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v2_reward/special_tokens_map.json
hastagaras-halu-8b-llama-4027-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v2_reward/config.json
hastagaras-halu-8b-llama-4027-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v2_reward/vocab.json
hastagaras-halu-8b-llama-4027-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v2_reward/tokenizer.json
hastagaras-halu-8b-llama-4027-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v2_reward/reward.tensors
Job hastagaras-halu-8b-llama-4027-v2-mkmlizer completed after 73.33s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-4027-v2-mkmlizer
Pipeline stage MKMLizer completed in 74.00s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-4027-v2
Waiting for inference service hastagaras-halu-8b-llama-4027-v2 to be ready
Inference service hastagaras-halu-8b-llama-4027-v2 ready after 50.252867460250854s
Pipeline stage ISVCDeployer completed in 56.06s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1355273723602295s
Received healthy response to inference request in 1.3570845127105713s
Received healthy response to inference request in 1.325171947479248s
Received healthy response to inference request in 1.2882418632507324s
Received healthy response to inference request in 1.243769645690918s
5 requests
0 failed requests
5th percentile: 1.2526640892028809
10th percentile: 1.2615585327148438
20th percentile: 1.2793474197387695
30th percentile: 1.2956278800964356
40th percentile: 1.3103999137878417
50th percentile: 1.325171947479248
60th percentile: 1.3379369735717774
70th percentile: 1.3507019996643066
80th percentile: 1.512773084640503
90th percentile: 1.8241502285003663
95th percentile: 1.9798388004302978
99th percentile: 2.104389657974243
mean time: 1.4699590682983399
Pipeline stage StressChecker completed in 8.04s
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-halu-8b-llama_4027_v2 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_4027_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics