submission_id: turboderp-llama3-turbca_4336_v12
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\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: 2024-06-28T20:49:44+00:00
model_name: turboderp-llama3-turbcat
model_group: turboderp/llama3-turbcat
num_battles: 20319
num_wins: 9958
celo_rating: 1177.12
propriety_score: 0.7130274874177314
propriety_total_count: 10332.0
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: 0.49008317338451696
Resubmit model
Running pipeline stage MKMLizer
Starting job with name turboderp-llama3-turbca-4336-v12-mkmlizer
Waiting for job on turboderp-llama3-turbca-4336-v12-mkmlizer to finish
turboderp-llama3-turbca-4336-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ _____ __ __ ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ /___/ ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ Version: 0.8.14 ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ https://mk1.ai ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ The license key for the current software has been verified as ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ belonging to: ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ Chai Research Corp. ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
turboderp-llama3-turbca-4336-v12-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-v12-mkmlizer: warnings.warn(warning_message, FutureWarning)
turboderp-llama3-turbca-4336-v12-mkmlizer: Downloaded to shared memory in 18.580s
turboderp-llama3-turbca-4336-v12-mkmlizer: quantizing model to /dev/shm/model_cache
turboderp-llama3-turbca-4336-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
turboderp-llama3-turbca-4336-v12-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 123.83it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 148.96it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 157.23it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 160.24it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 88.69it/s] Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 106.53it/s] Loading 0: 41%|████ | 120/291 [00:00<00:01, 121.85it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 134.37it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 143.85it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 148.76it/s] Loading 0: 65%|██████▌ | 190/291 [00:01<00:01, 86.40it/s] Loading 0: 71%|███████ | 207/291 [00:01<00:00, 100.84it/s] Loading 0: 77%|███████▋ | 224/291 [00:01<00:00, 114.36it/s] Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 122.00it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 133.99it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 143.06it/s] Loading 0: 100%|██████████| 291/291 [00:07<00:00, 9.83it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
turboderp-llama3-turbca-4336-v12-mkmlizer: quantized model in 23.091s
turboderp-llama3-turbca-4336-v12-mkmlizer: Processed model turboderp/llama3-turbcat-instruct-8b in 44.170s
turboderp-llama3-turbca-4336-v12-mkmlizer: creating bucket guanaco-mkml-models
turboderp-llama3-turbca-4336-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
turboderp-llama3-turbca-4336-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v12
turboderp-llama3-turbca-4336-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v12/tokenizer_config.json
turboderp-llama3-turbca-4336-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v12/special_tokens_map.json
turboderp-llama3-turbca-4336-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v12/flywheel_model.0.safetensors
turboderp-llama3-turbca-4336-v12-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
turboderp-llama3-turbca-4336-v12-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-v12-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v12-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-v12-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v12-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-v12-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v12-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-v12-mkmlizer: return self.fget.__get__(instance, owner)()
turboderp-llama3-turbca-4336-v12-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
turboderp-llama3-turbca-4336-v12-mkmlizer: Saving duration: 0.388s
turboderp-llama3-turbca-4336-v12-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.952s
turboderp-llama3-turbca-4336-v12-mkmlizer: creating bucket guanaco-reward-models
turboderp-llama3-turbca-4336-v12-mkmlizer: Bucket 's3://guanaco-reward-models/' created
turboderp-llama3-turbca-4336-v12-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v12_reward
turboderp-llama3-turbca-4336-v12-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v12_reward/config.json
turboderp-llama3-turbca-4336-v12-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v12_reward/special_tokens_map.json
turboderp-llama3-turbca-4336-v12-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v12_reward/tokenizer_config.json
turboderp-llama3-turbca-4336-v12-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v12_reward/merges.txt
turboderp-llama3-turbca-4336-v12-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v12_reward/vocab.json
turboderp-llama3-turbca-4336-v12-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v12_reward/tokenizer.json
turboderp-llama3-turbca-4336-v12-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v12_reward/reward.tensors
Job turboderp-llama3-turbca-4336-v12-mkmlizer completed after 73.98s with status: succeeded
Stopping job with name turboderp-llama3-turbca-4336-v12-mkmlizer
Pipeline stage MKMLizer completed in 75.35s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service turboderp-llama3-turbca-4336-v12
Waiting for inference service turboderp-llama3-turbca-4336-v12 to be ready
Inference service turboderp-llama3-turbca-4336-v12 ready after 100.64730882644653s
Pipeline stage ISVCDeployer completed in 107.49s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1045355796813965s
Received healthy response to inference request in 1.352400302886963s
Received healthy response to inference request in 1.3013927936553955s
Received healthy response to inference request in 1.2613327503204346s
Received healthy response to inference request in 1.3531522750854492s
5 requests
0 failed requests
5th percentile: 1.2693447589874267
10th percentile: 1.2773567676544189
20th percentile: 1.2933807849884034
30th percentile: 1.311594295501709
40th percentile: 1.3319972991943358
50th percentile: 1.352400302886963
60th percentile: 1.3527010917663573
70th percentile: 1.353001880645752
80th percentile: 1.503428936004639
90th percentile: 1.8039822578430176
95th percentile: 1.9542589187622068
99th percentile: 2.0744802474975588
mean time: 1.4745627403259278
Pipeline stage StressChecker completed in 8.09s
turboderp-llama3-turbca_4336_v12 status is now deployed due to DeploymentManager action
turboderp-llama3-turbca_4336_v12 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics