submission_id: turboderp-llama3-turbca_4336_v17
developer_uid: Lina09
status: inactive
model_repo: turboderp/llama3-turbcat-instruct-8b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.8, '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': '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{memory}<|eot_id|>', 'prompt_template': '<|start_header_id|>system<|end_header_id|>\n\nThe following message provides the necessary information about the below conversation and the characters in the conversation.\n{prompt}\nThe conversation below will be carried out according to information in the above text.<|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: 2024-07-03T09:41:16+00:00
model_name: turboderp-llama3-turbcat
model_group: turboderp/llama3-turbcat
num_battles: 17233
num_wins: 8589
celo_rating: 1182.95
propriety_score: 0.7079129694907014
propriety_total_count: 8227.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: turboderp-llama3-turbcat
ineligible_reason: None
language_model: turboderp/llama3-turbcat-instruct-8b
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-03
win_ratio: 0.4984042244530842
Resubmit model
Running pipeline stage MKMLizer
Starting job with name turboderp-llama3-turbca-4336-v17-mkmlizer
Waiting for job on turboderp-llama3-turbca-4336-v17-mkmlizer to finish
turboderp-llama3-turbca-4336-v17-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ _____ __ __ ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ /___/ ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ Version: 0.8.14 ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ https://mk1.ai ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ The license key for the current software has been verified as ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ belonging to: ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ Chai Research Corp. ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v17-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
turboderp-llama3-turbca-4336-v17-mkmlizer: Downloaded to shared memory in 38.316s
turboderp-llama3-turbca-4336-v17-mkmlizer: quantizing model to /dev/shm/model_cache
turboderp-llama3-turbca-4336-v17-mkmlizer: Saving flywheel model at /dev/shm/model_cache
turboderp-llama3-turbca-4336-v17-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 37.10it/s] Loading 0: 6%|▌ | 18/291 [00:00<00:02, 92.66it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 103.41it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:02, 116.37it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 116.54it/s] Loading 0: 25%|██▍ | 72/291 [00:00<00:01, 122.12it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:03, 55.87it/s] Loading 0: 34%|███▍ | 99/291 [00:01<00:02, 69.66it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 79.03it/s] Loading 0: 43%|████▎ | 125/291 [00:01<00:01, 88.96it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 91.38it/s] Loading 0: 52%|█████▏ | 150/291 [00:01<00:01, 94.74it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 104.57it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:01, 111.23it/s] Loading 0: 66%|██████▌ | 191/291 [00:02<00:01, 55.91it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 63.18it/s] Loading 0: 74%|███████▍ | 216/291 [00:02<00:00, 76.31it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 84.87it/s] Loading 0: 84%|████████▎ | 243/291 [00:02<00:00, 96.33it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 102.61it/s] Loading 0: 93%|█████████▎| 270/291 [00:03<00:00, 110.67it/s] Loading 0: 97%|█████████▋| 283/291 [00:03<00:00, 110.83it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
turboderp-llama3-turbca-4336-v17-mkmlizer: quantized model in 29.730s
turboderp-llama3-turbca-4336-v17-mkmlizer: Processed model turboderp/llama3-turbcat-instruct-8b in 68.047s
turboderp-llama3-turbca-4336-v17-mkmlizer: creating bucket guanaco-mkml-models
turboderp-llama3-turbca-4336-v17-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
turboderp-llama3-turbca-4336-v17-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v17
turboderp-llama3-turbca-4336-v17-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v17/special_tokens_map.json
turboderp-llama3-turbca-4336-v17-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v17/config.json
turboderp-llama3-turbca-4336-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v17/tokenizer_config.json
turboderp-llama3-turbca-4336-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v17/tokenizer.json
turboderp-llama3-turbca-4336-v17-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v17/flywheel_model.0.safetensors
turboderp-llama3-turbca-4336-v17-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
turboderp-llama3-turbca-4336-v17-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.
turboderp-llama3-turbca-4336-v17-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v17-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`.
turboderp-llama3-turbca-4336-v17-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v17-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.
turboderp-llama3-turbca-4336-v17-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v17-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.
turboderp-llama3-turbca-4336-v17-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v17-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()
turboderp-llama3-turbca-4336-v17-mkmlizer: return self.fget.__get__(instance, owner)()
turboderp-llama3-turbca-4336-v17-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
turboderp-llama3-turbca-4336-v17-mkmlizer: Saving duration: 0.528s
turboderp-llama3-turbca-4336-v17-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.432s
turboderp-llama3-turbca-4336-v17-mkmlizer: creating bucket guanaco-reward-models
turboderp-llama3-turbca-4336-v17-mkmlizer: Bucket 's3://guanaco-reward-models/' created
turboderp-llama3-turbca-4336-v17-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v17_reward
turboderp-llama3-turbca-4336-v17-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v17_reward/config.json
turboderp-llama3-turbca-4336-v17-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v17_reward/tokenizer_config.json
turboderp-llama3-turbca-4336-v17-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v17_reward/merges.txt
turboderp-llama3-turbca-4336-v17-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v17_reward/tokenizer.json
turboderp-llama3-turbca-4336-v17-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v17_reward/vocab.json
turboderp-llama3-turbca-4336-v17-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v17_reward/special_tokens_map.json
turboderp-llama3-turbca-4336-v17-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v17_reward/reward.tensors
Job turboderp-llama3-turbca-4336-v17-mkmlizer completed after 103.93s with status: succeeded
Stopping job with name turboderp-llama3-turbca-4336-v17-mkmlizer
Pipeline stage MKMLizer completed in 104.84s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service turboderp-llama3-turbca-4336-v17
Waiting for inference service turboderp-llama3-turbca-4336-v17 to be ready
Inference service turboderp-llama3-turbca-4336-v17 ready after 40.19794273376465s
Pipeline stage ISVCDeployer completed in 47.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.063197612762451s
Received healthy response to inference request in 1.3351025581359863s
Received healthy response to inference request in 1.294968843460083s
Received healthy response to inference request in 1.2520296573638916s
Received healthy response to inference request in 1.3636808395385742s
5 requests
0 failed requests
5th percentile: 1.2606174945831299
10th percentile: 1.2692053318023682
20th percentile: 1.2863810062408447
30th percentile: 1.3029955863952636
40th percentile: 1.319049072265625
50th percentile: 1.3351025581359863
60th percentile: 1.3465338706970216
70th percentile: 1.3579651832580566
80th percentile: 1.5035841941833497
90th percentile: 1.7833909034729005
95th percentile: 1.9232942581176757
99th percentile: 2.035216941833496
mean time: 1.4617959022521974
Pipeline stage StressChecker completed in 8.01s
turboderp-llama3-turbca_4336_v17 status is now deployed due to DeploymentManager action
turboderp-llama3-turbca_4336_v17 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics