submission_id: turboderp-llama3-turbca_4336_v11
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\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: 2024-06-27T23:11:54+00:00
model_name: turboderp-llama3-turbcat
model_group: turboderp/llama3-turbcat
num_battles: 23410
num_wins: 11547
celo_rating: 1179.79
propriety_score: 0.6980889378904814
propriety_total_count: 10884.0
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: 2024-06-27
win_ratio: 0.49325074754378473
Resubmit model
Running pipeline stage MKMLizer
Starting job with name turboderp-llama3-turbca-4336-v11-mkmlizer
Waiting for job on turboderp-llama3-turbca-4336-v11-mkmlizer to finish
turboderp-llama3-turbca-4336-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ _____ __ __ ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ /___/ ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ Version: 0.8.14 ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ https://mk1.ai ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ The license key for the current software has been verified as ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ belonging to: ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ Chai Research Corp. ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
turboderp-llama3-turbca-4336-v11-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-v11-mkmlizer: warnings.warn(warning_message, FutureWarning)
turboderp-llama3-turbca-4336-v11-mkmlizer: Downloaded to shared memory in 23.851s
turboderp-llama3-turbca-4336-v11-mkmlizer: quantizing model to /dev/shm/model_cache
turboderp-llama3-turbca-4336-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
turboderp-llama3-turbca-4336-v11-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 117.71it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 139.95it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 134.61it/s] Loading 0: 20%|██ | 59/291 [00:00<00:01, 126.32it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:01, 134.96it/s] Loading 0: 31%|███ | 90/291 [00:00<00:02, 72.63it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 85.18it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:01, 103.06it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 118.09it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 129.77it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 147.81it/s] Loading 0: 67%|██████▋ | 196/291 [00:01<00:01, 87.61it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 99.23it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 114.12it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 126.20it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 137.29it/s] Loading 0: 98%|█████████▊| 284/291 [00:02<00:00, 147.62it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
turboderp-llama3-turbca-4336-v11-mkmlizer: quantized model in 22.992s
turboderp-llama3-turbca-4336-v11-mkmlizer: Processed model turboderp/llama3-turbcat-instruct-8b in 49.504s
turboderp-llama3-turbca-4336-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v11/tokenizer_config.json
turboderp-llama3-turbca-4336-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v11/special_tokens_map.json
turboderp-llama3-turbca-4336-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v11/flywheel_model.0.safetensors
turboderp-llama3-turbca-4336-v11-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
turboderp-llama3-turbca-4336-v11-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-v11-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v11-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-v11-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v11-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-v11-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v11-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
turboderp-llama3-turbca-4336-v11-mkmlizer: Saving duration: 0.429s
turboderp-llama3-turbca-4336-v11-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.576s
turboderp-llama3-turbca-4336-v11-mkmlizer: creating bucket guanaco-reward-models
turboderp-llama3-turbca-4336-v11-mkmlizer: Bucket 's3://guanaco-reward-models/' created
turboderp-llama3-turbca-4336-v11-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v11_reward
turboderp-llama3-turbca-4336-v11-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v11_reward/config.json
turboderp-llama3-turbca-4336-v11-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v11_reward/special_tokens_map.json
turboderp-llama3-turbca-4336-v11-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v11_reward/vocab.json
turboderp-llama3-turbca-4336-v11-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v11_reward/tokenizer_config.json
turboderp-llama3-turbca-4336-v11-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v11_reward/merges.txt
turboderp-llama3-turbca-4336-v11-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v11_reward/tokenizer.json
turboderp-llama3-turbca-4336-v11-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v11_reward/reward.tensors
Job turboderp-llama3-turbca-4336-v11-mkmlizer completed after 76.69s with status: succeeded
Stopping job with name turboderp-llama3-turbca-4336-v11-mkmlizer
Pipeline stage MKMLizer completed in 77.66s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service turboderp-llama3-turbca-4336-v11
Waiting for inference service turboderp-llama3-turbca-4336-v11 to be ready
Connection pool is full, discarding connection: %s
Inference service turboderp-llama3-turbca-4336-v11 ready after 40.341137409210205s
Pipeline stage ISVCDeployer completed in 48.54s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1935317516326904s
Received healthy response to inference request in 1.3317787647247314s
Received healthy response to inference request in 1.2764077186584473s
Received healthy response to inference request in 1.3607206344604492s
Received healthy response to inference request in 1.3596670627593994s
5 requests
0 failed requests
5th percentile: 1.287481927871704
10th percentile: 1.298556137084961
20th percentile: 1.3207045555114747
30th percentile: 1.3373564243316651
40th percentile: 1.3485117435455323
50th percentile: 1.3596670627593994
60th percentile: 1.3600884914398192
70th percentile: 1.3605099201202393
80th percentile: 1.5272828578948976
90th percentile: 1.8604073047637941
95th percentile: 2.026969528198242
99th percentile: 2.160219306945801
mean time: 1.5044211864471435
Pipeline stage StressChecker completed in 8.31s
turboderp-llama3-turbca_4336_v11 status is now deployed due to DeploymentManager action
turboderp-llama3-turbca_4336_v11 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics