submission_id: turboderp-llama3-turbcat_4336_v4
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': '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{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: 2024-06-26T18:53:54+00:00
model_name: turboderp-llama3-turbcat
model_group: turboderp/llama3-turbcat
num_battles: 14188
num_wins: 6918
celo_rating: 1182.78
propriety_score: 0.7046879665571812
propriety_total_count: 6698.0
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: 2024-06-26
win_ratio: 0.48759515083168875
Resubmit model
Running pipeline stage MKMLizer
Starting job with name turboderp-llama3-turbcat-4336-v4-mkmlizer
Waiting for job on turboderp-llama3-turbcat-4336-v4-mkmlizer to finish
turboderp-llama3-turbcat-4336-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ _____ __ __ ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ /___/ ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ Version: 0.8.14 ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ https://mk1.ai ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ The license key for the current software has been verified as ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ belonging to: ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ Chai Research Corp. ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ║ ║
turboderp-llama3-turbcat-4336-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
turboderp-llama3-turbcat-4336-v4-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-turbcat-4336-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
turboderp-llama3-turbcat-4336-v4-mkmlizer: Downloaded to shared memory in 25.147s
turboderp-llama3-turbcat-4336-v4-mkmlizer: quantizing model to /dev/shm/model_cache
turboderp-llama3-turbcat-4336-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
turboderp-llama3-turbcat-4336-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 117.63it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 95.25it/s] Loading 0: 12%|█▏ | 35/291 [00:00<00:02, 99.30it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:02, 102.00it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 105.31it/s] Loading 0: 24%|██▎ | 69/291 [00:00<00:02, 101.43it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:02, 103.45it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:04, 49.89it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:03, 61.13it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:02, 67.01it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 86.17it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 86.29it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 102.38it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 97.96it/s] Loading 0: 62%|██████▏ | 181/291 [00:02<00:01, 105.51it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 58.62it/s] Loading 0: 71%|███████ | 206/291 [00:02<00:01, 70.15it/s] Loading 0: 74%|███████▍ | 216/291 [00:02<00:00, 75.55it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 83.00it/s] Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 87.07it/s] Loading 0: 88%|████████▊ | 255/291 [00:03<00:00, 100.84it/s] Loading 0: 92%|█████████▏| 267/291 [00:03<00:00, 95.10it/s] Loading 0: 96%|█████████▌| 278/291 [00:03<00:00, 97.77it/s] Loading 0: 99%|█████████▉| 289/291 [00:09<00:00, 6.47it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
turboderp-llama3-turbcat-4336-v4-mkmlizer: quantized model in 20.598s
turboderp-llama3-turbcat-4336-v4-mkmlizer: Processed model turboderp/llama3-turbcat-instruct-8b in 47.123s
turboderp-llama3-turbcat-4336-v4-mkmlizer: creating bucket guanaco-mkml-models
turboderp-llama3-turbcat-4336-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
turboderp-llama3-turbcat-4336-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/turboderp-llama3-turbcat-4336-v4
turboderp-llama3-turbcat-4336-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/turboderp-llama3-turbcat-4336-v4/flywheel_model.0.safetensors
turboderp-llama3-turbcat-4336-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
turboderp-llama3-turbcat-4336-v4-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-turbcat-4336-v4-mkmlizer: warnings.warn(
turboderp-llama3-turbcat-4336-v4-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-turbcat-4336-v4-mkmlizer: warnings.warn(
turboderp-llama3-turbcat-4336-v4-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-turbcat-4336-v4-mkmlizer: warnings.warn(
turboderp-llama3-turbcat-4336-v4-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-turbcat-4336-v4-mkmlizer: return self.fget.__get__(instance, owner)()
turboderp-llama3-turbcat-4336-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
turboderp-llama3-turbcat-4336-v4-mkmlizer: Saving duration: 0.284s
turboderp-llama3-turbcat-4336-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.047s
turboderp-llama3-turbcat-4336-v4-mkmlizer: creating bucket guanaco-reward-models
turboderp-llama3-turbcat-4336-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
turboderp-llama3-turbcat-4336-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v4_reward
turboderp-llama3-turbcat-4336-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v4_reward/config.json
turboderp-llama3-turbcat-4336-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v4_reward/special_tokens_map.json
turboderp-llama3-turbcat-4336-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v4_reward/tokenizer_config.json
turboderp-llama3-turbcat-4336-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v4_reward/merges.txt
turboderp-llama3-turbcat-4336-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v4_reward/vocab.json
turboderp-llama3-turbcat-4336-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v4_reward/tokenizer.json
turboderp-llama3-turbcat-4336-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v4_reward/reward.tensors
Job turboderp-llama3-turbcat-4336-v4-mkmlizer completed after 74.0s with status: succeeded
Stopping job with name turboderp-llama3-turbcat-4336-v4-mkmlizer
Pipeline stage MKMLizer completed in 74.93s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.15s
Running pipeline stage ISVCDeployer
Creating inference service turboderp-llama3-turbcat-4336-v4
Waiting for inference service turboderp-llama3-turbcat-4336-v4 to be ready
Inference service turboderp-llama3-turbcat-4336-v4 ready after 40.315372705459595s
Pipeline stage ISVCDeployer completed in 47.13s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.228445053100586s
Received healthy response to inference request in 1.303278923034668s
Received healthy response to inference request in 1.4582247734069824s
Received healthy response to inference request in 1.369511604309082s
Received healthy response to inference request in 1.334831953048706s
5 requests
0 failed requests
5th percentile: 1.3095895290374755
10th percentile: 1.3159001350402832
20th percentile: 1.3285213470458985
30th percentile: 1.3417678833007813
40th percentile: 1.3556397438049317
50th percentile: 1.369511604309082
60th percentile: 1.4049968719482422
70th percentile: 1.4404821395874023
80th percentile: 1.6122688293457033
90th percentile: 1.9203569412231447
95th percentile: 2.074400997161865
99th percentile: 2.197636241912842
mean time: 1.538858461380005
Pipeline stage StressChecker completed in 8.56s
turboderp-llama3-turbcat_4336_v4 status is now deployed due to DeploymentManager action
turboderp-llama3-turbcat_4336_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics