submission_id: cgato-thespice-l3-8b-v0-_3216_v2
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSpice-L3-8b-v0.3.2-Base
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 200, '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': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}
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': True}
timestamp: 2024-06-18T19:55:53+00:00
model_name: cgato-thespice-l3-8b-v0-_3216_v2
model_group: cgato/TheSpice-L3-8b-v0.
num_battles: 18811
num_wins: 9722
celo_rating: 1197.52
propriety_score: 0.7163805842900989
propriety_total_count: 8797.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030294016.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-thespice-l3-8b-v0-_3216_v2
ineligible_reason: None
language_model: cgato/TheSpice-L3-8b-v0.3.2-Base
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-18
win_ratio: 0.5168252618148955
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespice-l3-8b-v0-3216-v2-mkmlizer
Waiting for job on cgato-thespice-l3-8b-v0-3216-v2-mkmlizer to finish
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ _____ __ __ ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ /___/ ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ Version: 0.8.14 ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ https://mk1.ai ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ belonging to: ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ║ ║
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespice-l3-8b-v0-3216-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.
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: Downloaded to shared memory in 24.572s
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 6%|▌ | 18/291 [00:00<00:01, 179.53it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:01, 188.45it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 184.43it/s] Loading 0: 26%|██▋ | 77/291 [00:00<00:01, 182.24it/s] Loading 0: 33%|███▎ | 96/291 [00:00<00:02, 84.23it/s] Loading 0: 40%|████ | 117/291 [00:00<00:01, 107.32it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 128.40it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:00, 141.45it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:00, 159.89it/s] Loading 0: 69%|██████▊ | 200/291 [00:01<00:00, 99.74it/s] Loading 0: 75%|███████▌ | 219/291 [00:01<00:00, 115.27it/s] Loading 0: 82%|████████▏ | 238/291 [00:01<00:00, 129.92it/s] Loading 0: 89%|████████▊ | 258/291 [00:01<00:00, 145.32it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 162.01it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: quantized model in 18.320s
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: Processed model cgato/TheSpice-L3-8b-v0.3.2-Base in 43.903s
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespice-l3-8b-v0-3216-v2
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespice-l3-8b-v0-3216-v2/config.json
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespice-l3-8b-v0-3216-v2/special_tokens_map.json
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespice-l3-8b-v0-3216-v2/tokenizer_config.json
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespice-l3-8b-v0-3216-v2/tokenizer.json
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thespice-l3-8b-v0-3216-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.
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: warnings.warn(
cgato-thespice-l3-8b-v0-3216-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.
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: warnings.warn(
cgato-thespice-l3-8b-v0-3216-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.
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: warnings.warn(
cgato-thespice-l3-8b-v0-3216-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()
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: Saving duration: 0.269s
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.009s
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thespice-l3-8b-v0-3216-v2_reward
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thespice-l3-8b-v0-3216-v2_reward/config.json
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thespice-l3-8b-v0-3216-v2_reward/special_tokens_map.json
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thespice-l3-8b-v0-3216-v2_reward/tokenizer_config.json
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thespice-l3-8b-v0-3216-v2_reward/merges.txt
cgato-thespice-l3-8b-v0-3216-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thespice-l3-8b-v0-3216-v2_reward/reward.tensors
Job cgato-thespice-l3-8b-v0-3216-v2-mkmlizer completed after 76.87s with status: succeeded
Stopping job with name cgato-thespice-l3-8b-v0-3216-v2-mkmlizer
Pipeline stage MKMLizer completed in 80.38s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespice-l3-8b-v0-3216-v2
Waiting for inference service cgato-thespice-l3-8b-v0-3216-v2 to be ready
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v33: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))
Inference service cgato-thespice-l3-8b-v0-3216-v2 ready after 40.25614023208618s
Pipeline stage ISVCDeployer completed in 47.91s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0774056911468506s
Received healthy response to inference request in 3.8045437335968018s
Received healthy response to inference request in 1.1834185123443604s
Received healthy response to inference request in 1.2471811771392822s
Received healthy response to inference request in 1.259488582611084s
5 requests
0 failed requests
5th percentile: 1.1961710453033447
10th percentile: 1.208923578262329
20th percentile: 1.2344286441802979
30th percentile: 1.2496426582336426
40th percentile: 1.2545656204223632
50th percentile: 1.259488582611084
60th percentile: 1.5866554260253904
70th percentile: 1.9138222694396971
80th percentile: 2.4228332996368414
90th percentile: 3.1136885166168216
95th percentile: 3.459116125106811
99th percentile: 3.735458211898804
mean time: 1.9144075393676758
Pipeline stage StressChecker completed in 10.24s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cgato-thespice-l3-8b-v0-_3216_v2 status is now deployed due to DeploymentManager action
cgato-thespice-l3-8b-v0-_3216_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics