submission_id: turboderp-llama3-turbca_4336_v14
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': '{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: 2024-06-30T04:10:51+00:00
model_name: turboderp-llama3-turbcat
model_group: turboderp/llama3-turbcat
num_battles: 29043
num_wins: 14594
celo_rating: 1184.4
propriety_score: 0.6835743578674724
propriety_total_count: 13899.0
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: 2024-06-29
win_ratio: 0.5024962985917433
Resubmit model
Running pipeline stage MKMLizer
Running pipeline stage MKMLizer
Starting job with name turboderp-llama3-turbca-4336-v14-mkmlizer
Stopping job with name turboderp-llama3-turbca-4336-v14-mkmlizer
%s, retrying in %s seconds...
Stopping job with name turboderp-llama3-turbca-4336-v14-mkmlizer
%s, retrying in %s seconds...
Starting job with name turboderp-llama3-turbca-4336-v14-mkmlizer
Waiting for job on turboderp-llama3-turbca-4336-v14-mkmlizer to finish
turboderp-llama3-turbca-4336-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ _____ __ __ ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ /___/ ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ Version: 0.8.14 ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ https://mk1.ai ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ The license key for the current software has been verified as ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ belonging to: ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ Chai Research Corp. ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
turboderp-llama3-turbca-4336-v14-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-v14-mkmlizer: warnings.warn(warning_message, FutureWarning)
turboderp-llama3-turbca-4336-v14-mkmlizer: Downloaded to shared memory in 18.321s
turboderp-llama3-turbca-4336-v14-mkmlizer: quantizing model to /dev/shm/model_cache
turboderp-llama3-turbca-4336-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
turboderp-llama3-turbca-4336-v14-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 117.76it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 146.94it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 156.53it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 160.00it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 84.87it/s] Loading 0: 33%|███▎ | 96/291 [00:00<00:02, 78.62it/s] Loading 0: 37%|███▋ | 107/291 [00:01<00:02, 80.91it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 88.99it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 107.15it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 121.58it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 130.87it/s] Loading 0: 65%|██████▍ | 188/291 [00:01<00:01, 84.53it/s] Loading 0: 69%|██████▊ | 200/291 [00:02<00:01, 84.30it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:00, 88.67it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 107.21it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 121.87it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 134.62it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 141.62it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
turboderp-llama3-turbca-4336-v14-mkmlizer: quantized model in 23.123s
turboderp-llama3-turbca-4336-v14-mkmlizer: creating bucket guanaco-mkml-models
turboderp-llama3-turbca-4336-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
turboderp-llama3-turbca-4336-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v14
turboderp-llama3-turbca-4336-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v14/config.json
turboderp-llama3-turbca-4336-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v14/tokenizer_config.json
turboderp-llama3-turbca-4336-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v14/special_tokens_map.json
turboderp-llama3-turbca-4336-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v14/tokenizer.json
turboderp-llama3-turbca-4336-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v14/flywheel_model.0.safetensors
turboderp-llama3-turbca-4336-v14-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
turboderp-llama3-turbca-4336-v14-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-v14-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v14-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-v14-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v14-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-v14-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v14-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-v14-mkmlizer: return self.fget.__get__(instance, owner)()
turboderp-llama3-turbca-4336-v14-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
turboderp-llama3-turbca-4336-v14-mkmlizer: Saving duration: 0.394s
turboderp-llama3-turbca-4336-v14-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.352s
turboderp-llama3-turbca-4336-v14-mkmlizer: creating bucket guanaco-reward-models
turboderp-llama3-turbca-4336-v14-mkmlizer: Bucket 's3://guanaco-reward-models/' created
turboderp-llama3-turbca-4336-v14-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v14_reward
turboderp-llama3-turbca-4336-v14-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v14_reward/config.json
turboderp-llama3-turbca-4336-v14-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v14_reward/special_tokens_map.json
turboderp-llama3-turbca-4336-v14-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v14_reward/tokenizer_config.json
turboderp-llama3-turbca-4336-v14-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v14_reward/merges.txt
turboderp-llama3-turbca-4336-v14-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v14_reward/vocab.json
turboderp-llama3-turbca-4336-v14-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v14_reward/tokenizer.json
turboderp-llama3-turbca-4336-v14-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v14_reward/reward.tensors
Job turboderp-llama3-turbca-4336-v14-mkmlizer completed after 107.92s with status: succeeded
Stopping job with name turboderp-llama3-turbca-4336-v14-mkmlizer
Pipeline stage MKMLizer completed in 109.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service turboderp-llama3-turbca-4336-v14
Waiting for inference service turboderp-llama3-turbca-4336-v14 to be ready
Inference service turboderp-llama3-turbca-4336-v14 ready after 50.22732138633728s
Pipeline stage ISVCDeployer completed in 57.08s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.568702459335327s
Received healthy response to inference request in 1.386061429977417s
Received healthy response to inference request in 1.350001335144043s
Received healthy response to inference request in 1.2981202602386475s
Received healthy response to inference request in 1.3736600875854492s
5 requests
0 failed requests
5th percentile: 1.3084964752197266
10th percentile: 1.3188726902008057
20th percentile: 1.3396251201629639
30th percentile: 1.3547330856323243
40th percentile: 1.3641965866088868
50th percentile: 1.3736600875854492
60th percentile: 1.3786206245422363
70th percentile: 1.3835811614990234
80th percentile: 1.6225896358489993
90th percentile: 2.095646047592163
95th percentile: 2.332174253463745
99th percentile: 2.5213968181610107
mean time: 1.5953091144561768
Pipeline stage StressChecker completed in 8.74s
turboderp-llama3-turbca_4336_v14 status is now deployed due to DeploymentManager action
turboderp-llama3-turbca_4336_v14 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics