submission_id: turboderp-llama3-turbcat_4336_v2
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: 2024-06-26T18:48:47+00:00
model_name: turboderp-llama3-turbcat_4336_v2
model_group: turboderp/llama3-turbcat
num_battles: 14137
num_wins: 6743
celo_rating: 1175.75
propriety_score: 0.7072877535687453
propriety_total_count: 6655.0
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_4336_v2
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: 0.4769753130084176
Resubmit model
Running pipeline stage MKMLizer
Starting job with name turboderp-llama3-turbcat-4336-v2-mkmlizer
Waiting for job on turboderp-llama3-turbcat-4336-v2-mkmlizer to finish
turboderp-llama3-turbcat-4336-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ _____ __ __ ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ /___/ ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ Version: 0.8.14 ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ https://mk1.ai ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ The license key for the current software has been verified as ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ belonging to: ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ Chai Research Corp. ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ║ ║
turboderp-llama3-turbcat-4336-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
turboderp-llama3-turbcat-4336-v2-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-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
turboderp-llama3-turbcat-4336-v2-mkmlizer: Downloaded to shared memory in 29.303s
turboderp-llama3-turbcat-4336-v2-mkmlizer: quantizing model to /dev/shm/model_cache
turboderp-llama3-turbcat-4336-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
turboderp-llama3-turbcat-4336-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 117.76it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 114.25it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 125.27it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:01, 133.56it/s] Loading 0: 24%|██▍ | 71/291 [00:00<00:01, 130.15it/s] Loading 0: 29%|██▉ | 84/291 [00:01<00:04, 48.13it/s] Loading 0: 33%|███▎ | 95/291 [00:01<00:03, 56.87it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 74.09it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 90.03it/s] Loading 0: 49%|████▉ | 142/291 [00:01<00:01, 98.03it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 107.74it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:01, 117.02it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 59.40it/s] Loading 0: 68%|██████▊ | 198/291 [00:02<00:01, 65.89it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 75.89it/s] Loading 0: 78%|███████▊ | 226/291 [00:02<00:00, 90.36it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 96.59it/s] Loading 0: 87%|████████▋ | 252/291 [00:02<00:00, 106.82it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 111.37it/s] Loading 0: 97%|█████████▋| 281/291 [00:03<00:00, 118.79it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
turboderp-llama3-turbcat-4336-v2-mkmlizer: quantized model in 20.742s
turboderp-llama3-turbcat-4336-v2-mkmlizer: Processed model turboderp/llama3-turbcat-instruct-8b in 51.478s
turboderp-llama3-turbcat-4336-v2-mkmlizer: creating bucket guanaco-mkml-models
turboderp-llama3-turbcat-4336-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
turboderp-llama3-turbcat-4336-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/turboderp-llama3-turbcat-4336-v2
turboderp-llama3-turbcat-4336-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/turboderp-llama3-turbcat-4336-v2/config.json
turboderp-llama3-turbcat-4336-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/turboderp-llama3-turbcat-4336-v2/tokenizer_config.json
turboderp-llama3-turbcat-4336-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/turboderp-llama3-turbcat-4336-v2/special_tokens_map.json
turboderp-llama3-turbcat-4336-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/turboderp-llama3-turbcat-4336-v2/tokenizer.json
turboderp-llama3-turbcat-4336-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/turboderp-llama3-turbcat-4336-v2/flywheel_model.0.safetensors
turboderp-llama3-turbcat-4336-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
turboderp-llama3-turbcat-4336-v2-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-v2-mkmlizer: warnings.warn(
turboderp-llama3-turbcat-4336-v2-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-v2-mkmlizer: warnings.warn(
turboderp-llama3-turbcat-4336-v2-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-v2-mkmlizer: warnings.warn(
turboderp-llama3-turbcat-4336-v2-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-v2-mkmlizer: return self.fget.__get__(instance, owner)()
turboderp-llama3-turbcat-4336-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
turboderp-llama3-turbcat-4336-v2-mkmlizer: Saving duration: 0.274s
turboderp-llama3-turbcat-4336-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.374s
turboderp-llama3-turbcat-4336-v2-mkmlizer: creating bucket guanaco-reward-models
turboderp-llama3-turbcat-4336-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
turboderp-llama3-turbcat-4336-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v2_reward
turboderp-llama3-turbcat-4336-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v2_reward/config.json
turboderp-llama3-turbcat-4336-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v2_reward/special_tokens_map.json
turboderp-llama3-turbcat-4336-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v2_reward/tokenizer_config.json
turboderp-llama3-turbcat-4336-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v2_reward/merges.txt
turboderp-llama3-turbcat-4336-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v2_reward/vocab.json
turboderp-llama3-turbcat-4336-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v2_reward/tokenizer.json
turboderp-llama3-turbcat-4336-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v2_reward/reward.tensors
Job turboderp-llama3-turbcat-4336-v2-mkmlizer completed after 73.4s with status: succeeded
Stopping job with name turboderp-llama3-turbcat-4336-v2-mkmlizer
Pipeline stage MKMLizer completed in 74.33s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service turboderp-llama3-turbcat-4336-v2
Waiting for inference service turboderp-llama3-turbcat-4336-v2 to be ready
Inference service turboderp-llama3-turbcat-4336-v2 ready after 40.32836961746216s
Pipeline stage ISVCDeployer completed in 47.39s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.346658706665039s
Received healthy response to inference request in 1.4413163661956787s
Received healthy response to inference request in 1.2921123504638672s
Received healthy response to inference request in 1.3621726036071777s
Received healthy response to inference request in 1.3246312141418457s
5 requests
0 failed requests
5th percentile: 1.2986161231994628
10th percentile: 1.3051198959350585
20th percentile: 1.31812744140625
30th percentile: 1.332139492034912
40th percentile: 1.347156047821045
50th percentile: 1.3621726036071777
60th percentile: 1.3938301086425782
70th percentile: 1.4254876136779786
80th percentile: 1.622384834289551
90th percentile: 1.984521770477295
95th percentile: 2.1655902385711667
99th percentile: 2.3104450130462646
mean time: 1.5533782482147216
Pipeline stage StressChecker completed in 8.49s
turboderp-llama3-turbcat_4336_v2 status is now deployed due to DeploymentManager action
turboderp-llama3-turbcat_4336_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics