submission_id: turboderp-llama3-turbca_4336_v13
developer_uid: kaltcit
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\nBelow is an engaging conversation about romance and body interactions.{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: 2024-06-28T22:48:28+00:00
model_name: turboderp-llama3-turbcat
model_group: turboderp/llama3-turbcat
num_battles: 21382
num_wins: 10733
celo_rating: 1178.72
propriety_score: 0.7015825914935707
propriety_total_count: 10110.0
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: 2024-06-28
win_ratio: 0.501964269011318
Resubmit model
Running pipeline stage MKMLizer
Starting job with name turboderp-llama3-turbca-4336-v13-mkmlizer
Waiting for job on turboderp-llama3-turbca-4336-v13-mkmlizer to finish
turboderp-llama3-turbca-4336-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ _____ __ __ ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ /___/ ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ Version: 0.8.14 ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ https://mk1.ai ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ The license key for the current software has been verified as ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ belonging to: ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ Chai Research Corp. ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
turboderp-llama3-turbca-4336-v13-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.
turboderp-llama3-turbca-4336-v13-mkmlizer: warnings.warn(warning_message, FutureWarning)
turboderp-llama3-turbca-4336-v13-mkmlizer: Downloaded to shared memory in 26.503s
turboderp-llama3-turbca-4336-v13-mkmlizer: quantizing model to /dev/shm/model_cache
turboderp-llama3-turbca-4336-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
turboderp-llama3-turbca-4336-v13-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 112.98it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 136.66it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:01, 129.03it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 126.51it/s] Loading 0: 25%|██▌ | 73/291 [00:00<00:01, 133.96it/s] Loading 0: 30%|██▉ | 87/291 [00:00<00:03, 65.74it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 82.68it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:01, 99.88it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 114.51it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 126.62it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 145.40it/s] Loading 0: 67%|██████▋ | 196/291 [00:01<00:01, 88.34it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:00, 99.83it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 114.00it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 125.45it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 136.41it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 142.81it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
turboderp-llama3-turbca-4336-v13-mkmlizer: quantized model in 22.939s
turboderp-llama3-turbca-4336-v13-mkmlizer: Processed model turboderp/llama3-turbcat-instruct-8b in 52.064s
turboderp-llama3-turbca-4336-v13-mkmlizer: creating bucket guanaco-mkml-models
turboderp-llama3-turbca-4336-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
turboderp-llama3-turbca-4336-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v13
turboderp-llama3-turbca-4336-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v13/tokenizer_config.json
turboderp-llama3-turbca-4336-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v13/config.json
turboderp-llama3-turbca-4336-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v13/special_tokens_map.json
turboderp-llama3-turbca-4336-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v13/tokenizer.json
turboderp-llama3-turbca-4336-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v13/flywheel_model.0.safetensors
turboderp-llama3-turbca-4336-v13-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
turboderp-llama3-turbca-4336-v13-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.
turboderp-llama3-turbca-4336-v13-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v13-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.
turboderp-llama3-turbca-4336-v13-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v13-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-v13-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v13-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-v13-mkmlizer: return self.fget.__get__(instance, owner)()
turboderp-llama3-turbca-4336-v13-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
turboderp-llama3-turbca-4336-v13-mkmlizer: Saving duration: 0.432s
turboderp-llama3-turbca-4336-v13-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.070s
turboderp-llama3-turbca-4336-v13-mkmlizer: creating bucket guanaco-reward-models
turboderp-llama3-turbca-4336-v13-mkmlizer: Bucket 's3://guanaco-reward-models/' created
turboderp-llama3-turbca-4336-v13-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v13_reward
turboderp-llama3-turbca-4336-v13-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v13_reward/config.json
turboderp-llama3-turbca-4336-v13-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v13_reward/special_tokens_map.json
turboderp-llama3-turbca-4336-v13-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v13_reward/tokenizer_config.json
turboderp-llama3-turbca-4336-v13-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v13_reward/merges.txt
turboderp-llama3-turbca-4336-v13-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v13_reward/vocab.json
turboderp-llama3-turbca-4336-v13-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v13_reward/tokenizer.json
turboderp-llama3-turbca-4336-v13-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v13_reward/reward.tensors
Job turboderp-llama3-turbca-4336-v13-mkmlizer completed after 85.97s with status: succeeded
Stopping job with name turboderp-llama3-turbca-4336-v13-mkmlizer
Pipeline stage MKMLizer completed in 87.03s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service turboderp-llama3-turbca-4336-v13
Waiting for inference service turboderp-llama3-turbca-4336-v13 to be ready
Inference service turboderp-llama3-turbca-4336-v13 ready after 40.25458359718323s
Pipeline stage ISVCDeployer completed in 47.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2289814949035645s
Received healthy response to inference request in 1.3247356414794922s
Received healthy response to inference request in 1.2766542434692383s
Received healthy response to inference request in 1.3774049282073975s
Received healthy response to inference request in 1.3019440174102783s
5 requests
0 failed requests
5th percentile: 1.2817121982574462
10th percentile: 1.2867701530456543
20th percentile: 1.2968860626220704
30th percentile: 1.306502342224121
40th percentile: 1.3156189918518066
50th percentile: 1.3247356414794922
60th percentile: 1.3458033561706544
70th percentile: 1.3668710708618164
80th percentile: 1.5477202415466311
90th percentile: 1.8883508682250978
95th percentile: 2.058666181564331
99th percentile: 2.194918432235718
mean time: 1.5019440650939941
Pipeline stage StressChecker completed in 8.78s
turboderp-llama3-turbca_4336_v13 status is now deployed due to DeploymentManager action
turboderp-llama3-turbca_4336_v13 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics