developer_uid: Hastagaras
submission_id: hastagaras-llama-3-8b-okay_v15
model_name: test
model_group: Hastagaras/llama-3-8b-ok
status: torndown
timestamp: 2024-07-09T11:55:57+00:00
num_battles: 31504
num_wins: 11592
celo_rating: 1106.32
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/llama-3-8b-okay
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/CHAI_alignment_reward_model
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: test
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-okay
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-09
win_ratio: 0.3679532757745048
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|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: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-okay-v15-mkmlizer
Waiting for job on hastagaras-llama-3-8b-okay-v15-mkmlizer to finish
hastagaras-llama-3-8b-okay-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-okay-v15-mkmlizer: Downloaded to shared memory in 35.182s
hastagaras-llama-3-8b-okay-v15-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v15-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 127.94it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:01, 143.40it/s]
Loading 0:  15%|█▌        | 45/291 [00:00<00:01, 140.12it/s]
Loading 0:  20%|██        | 59/291 [00:00<00:01, 133.24it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:01, 140.33it/s]
Loading 0:  31%|███▏      | 91/291 [00:00<00:02, 68.15it/s] 
Loading 0:  36%|███▌      | 104/291 [00:01<00:02, 77.50it/s]
Loading 0:  42%|████▏     | 121/291 [00:01<00:01, 94.45it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:01, 108.88it/s]
Loading 0:  52%|█████▏    | 152/291 [00:01<00:01, 115.40it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:01, 114.11it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 120.29it/s]
Loading 0:  67%|██████▋   | 195/291 [00:02<00:01, 74.12it/s] 
Loading 0:  73%|███████▎  | 211/291 [00:02<00:00, 88.38it/s]
Loading 0:  78%|███████▊  | 228/291 [00:02<00:00, 103.35it/s]
Loading 0:  83%|████████▎ | 242/291 [00:02<00:00, 111.12it/s]
Loading 0:  88%|████████▊ | 257/291 [00:02<00:00, 116.27it/s]
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 127.43it/s]
Loading 0:  99%|█████████▉| 288/291 [00:08<00:00,  8.38it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-okay-v15-mkmlizer: quantized model in 23.891s
hastagaras-llama-3-8b-okay-v15-mkmlizer: Processed model Hastagaras/llama-3-8b-okay in 59.074s
hastagaras-llama-3-8b-okay-v15-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-okay-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-okay-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v15
hastagaras-llama-3-8b-okay-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v15/config.json
hastagaras-llama-3-8b-okay-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v15/special_tokens_map.json
hastagaras-llama-3-8b-okay-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v15/tokenizer_config.json
hastagaras-llama-3-8b-okay-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v15/tokenizer.json
hastagaras-llama-3-8b-okay-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v15/flywheel_model.0.safetensors
hastagaras-llama-3-8b-okay-v15-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
hastagaras-llama-3-8b-okay-v15-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-llama-3-8b-okay-v15-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v15-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
hastagaras-llama-3-8b-okay-v15-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v15-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-llama-3-8b-okay-v15-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v15-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-llama-3-8b-okay-v15-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v15-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-okay-v15-mkmlizer: Saving duration: 0.151s
hastagaras-llama-3-8b-okay-v15-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 2.523s
Job hastagaras-llama-3-8b-okay-v15-mkmlizer completed after 83.35s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-okay-v15-mkmlizer
Pipeline stage MKMLizer completed in 84.26s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-okay-v15
Waiting for inference service hastagaras-llama-3-8b-okay-v15 to be ready
Inference service hastagaras-llama-3-8b-okay-v15 ready after 40.17226719856262s
Pipeline stage ISVCDeployer completed in 47.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9520909786224365s
Received healthy response to inference request in 1.3148810863494873s
Received healthy response to inference request in 1.2690238952636719s
Received healthy response to inference request in 1.2464439868927002s
Received healthy response to inference request in 1.305948257446289s
5 requests
0 failed requests
5th percentile: 1.2509599685668946
10th percentile: 1.2554759502410888
20th percentile: 1.2645079135894775
30th percentile: 1.2764087677001954
40th percentile: 1.2911785125732422
50th percentile: 1.305948257446289
60th percentile: 1.3095213890075683
70th percentile: 1.3130945205688476
80th percentile: 1.4423230648040772
90th percentile: 1.6972070217132569
95th percentile: 1.8246490001678466
99th percentile: 1.9266025829315185
mean time: 1.417677640914917
Pipeline stage StressChecker completed in 7.94s
hastagaras-llama-3-8b-okay_v15 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-okay_v15 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-okay_v15
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-okay-v15 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.77s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v15/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v15/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v15/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v15/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v15/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v15_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v15_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v15_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v15_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v15_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v15_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v15_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.31s
hastagaras-llama-3-8b-okay_v15 status is now torndown due to DeploymentManager action