submission_id: turboderp-llama3-turbca_4336_v16
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: 2024-07-03T09:40:56+00:00
model_name: turboderp-llama3-turbcat
model_group: turboderp/llama3-turbcat
num_battles: 17606
num_wins: 8750
celo_rating: 1182.15
propriety_score: 0.7082059722548789
propriety_total_count: 8506.0
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: 0.4969896626150176
Resubmit model
Running pipeline stage MKMLizer
Starting job with name turboderp-llama3-turbca-4336-v16-mkmlizer
Waiting for job on turboderp-llama3-turbca-4336-v16-mkmlizer to finish
Connection pool is full, discarding connection: %s
turboderp-llama3-turbca-4336-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ _____ __ __ ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ /___/ ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ Version: 0.8.14 ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ https://mk1.ai ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ The license key for the current software has been verified as ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ belonging to: ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ Chai Research Corp. ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
turboderp-llama3-turbca-4336-v16-mkmlizer: Downloaded to shared memory in 16.637s
turboderp-llama3-turbca-4336-v16-mkmlizer: quantizing model to /dev/shm/model_cache
turboderp-llama3-turbca-4336-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
turboderp-llama3-turbca-4336-v16-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 96.50it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:03, 88.37it/s] Loading 0: 11%|█ | 32/291 [00:00<00:02, 86.68it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:02, 112.00it/s] Loading 0: 21%|██ | 60/291 [00:00<00:02, 102.10it/s] Loading 0: 25%|██▌ | 73/291 [00:00<00:01, 109.95it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:03, 61.01it/s] Loading 0: 33%|███▎ | 95/291 [00:01<00:02, 65.83it/s] Loading 0: 37%|███▋ | 107/291 [00:01<00:02, 76.51it/s] Loading 0: 40%|████ | 117/291 [00:01<00:02, 81.63it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 89.78it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 93.94it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 106.93it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 103.26it/s] Loading 0: 63%|██████▎ | 182/291 [00:01<00:00, 112.82it/s] Loading 0: 67%|██████▋ | 194/291 [00:02<00:01, 68.84it/s] Loading 0: 71%|███████▏ | 208/291 [00:02<00:01, 82.25it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 84.95it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 81.99it/s] Loading 0: 83%|████████▎ | 242/291 [00:02<00:00, 89.59it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 99.26it/s] Loading 0: 92%|█████████▏| 267/291 [00:03<00:00, 98.18it/s] Loading 0: 96%|█████████▌| 279/291 [00:03<00:00, 97.80it/s] Loading 0: 100%|█████████▉| 290/291 [00:08<00:00, 7.04it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
turboderp-llama3-turbca-4336-v16-mkmlizer: quantized model in 19.885s
turboderp-llama3-turbca-4336-v16-mkmlizer: Processed model turboderp/llama3-turbcat-instruct-8b in 36.522s
turboderp-llama3-turbca-4336-v16-mkmlizer: creating bucket guanaco-mkml-models
turboderp-llama3-turbca-4336-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
turboderp-llama3-turbca-4336-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v16
turboderp-llama3-turbca-4336-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v16/config.json
turboderp-llama3-turbca-4336-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v16/special_tokens_map.json
turboderp-llama3-turbca-4336-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v16/tokenizer_config.json
turboderp-llama3-turbca-4336-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v16/tokenizer.json
turboderp-llama3-turbca-4336-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v16/flywheel_model.0.safetensors
turboderp-llama3-turbca-4336-v16-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
turboderp-llama3-turbca-4336-v16-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-v16-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v16-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-v16-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v16-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-v16-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v16-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-v16-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v16-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-v16-mkmlizer: return self.fget.__get__(instance, owner)()
turboderp-llama3-turbca-4336-v16-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
turboderp-llama3-turbca-4336-v16-mkmlizer: Saving duration: 0.268s
turboderp-llama3-turbca-4336-v16-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.566s
turboderp-llama3-turbca-4336-v16-mkmlizer: creating bucket guanaco-reward-models
turboderp-llama3-turbca-4336-v16-mkmlizer: Bucket 's3://guanaco-reward-models/' created
turboderp-llama3-turbca-4336-v16-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v16_reward
turboderp-llama3-turbca-4336-v16-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v16_reward/config.json
turboderp-llama3-turbca-4336-v16-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v16_reward/tokenizer_config.json
turboderp-llama3-turbca-4336-v16-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v16_reward/special_tokens_map.json
turboderp-llama3-turbca-4336-v16-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v16_reward/vocab.json
turboderp-llama3-turbca-4336-v16-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v16_reward/merges.txt
turboderp-llama3-turbca-4336-v16-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v16_reward/tokenizer.json
turboderp-llama3-turbca-4336-v16-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v16_reward/reward.tensors
Job turboderp-llama3-turbca-4336-v16-mkmlizer completed after 137.72s with status: succeeded
Stopping job with name turboderp-llama3-turbca-4336-v16-mkmlizer
Pipeline stage MKMLizer completed in 138.66s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service turboderp-llama3-turbca-4336-v16
Waiting for inference service turboderp-llama3-turbca-4336-v16 to be ready
Inference service turboderp-llama3-turbca-4336-v16 ready after 40.1731071472168s
Pipeline stage ISVCDeployer completed in 47.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.062932014465332s
Received healthy response to inference request in 1.346386432647705s
Received healthy response to inference request in 1.3032267093658447s
Received healthy response to inference request in 1.2513115406036377s
Received healthy response to inference request in 1.3534276485443115s
5 requests
0 failed requests
5th percentile: 1.261694574356079
10th percentile: 1.2720776081085206
20th percentile: 1.2928436756134034
30th percentile: 1.3118586540222168
40th percentile: 1.329122543334961
50th percentile: 1.346386432647705
60th percentile: 1.3492029190063477
70th percentile: 1.3520194053649903
80th percentile: 1.4953285217285157
90th percentile: 1.7791302680969239
95th percentile: 1.9210311412811278
99th percentile: 2.034551839828491
mean time: 1.4634568691253662
Pipeline stage StressChecker completed in 8.09s
turboderp-llama3-turbca_4336_v16 status is now deployed due to DeploymentManager action
turboderp-llama3-turbca_4336_v16 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics