submission_id: cgato-thespice-l3-8b-v0-_3216_v4
developer_uid: c.gato
best_of: 16
celo_rating: 1193.51
display_name: cgato-thespice-l3-8b-v0-_3216_v4
family_friendly_score: 0.0
formatter: {'memory_template': '<|im_start|>system\n{memory}', 'prompt_template': '\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}
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}
is_internal_developer: False
language_model: cgato/TheSpice-L3-8b-v0.3.2-Base
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cgato/TheSpice-L3-8b-v0.
model_name: cgato-thespice-l3-8b-v0-_3216_v4
model_num_parameters: 8030294016.0
model_repo: cgato/TheSpice-L3-8b-v0.3.2-Base
model_size: 8B
num_battles: 13380
num_wins: 6862
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': True, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-06-18T20:24:44+00:00
us_pacific_date: 2024-06-18
win_ratio: 0.5128550074738416
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thespice-l3-8b-v0-3216-v4-mkmlizer
Waiting for job on cgato-thespice-l3-8b-v0-3216-v4-mkmlizer to finish
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ _____ __ __ ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ /___/ ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ Version: 0.8.14 ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ https://mk1.ai ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ belonging to: ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ Chai Research Corp. ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ║ ║
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thespice-l3-8b-v0-3216-v4-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-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: Downloaded to shared memory in 21.410s
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:01, 166.66it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:01, 167.87it/s] Loading 0: 18%|█▊ | 53/291 [00:00<00:01, 177.46it/s] Loading 0: 25%|██▍ | 72/291 [00:00<00:01, 181.14it/s] Loading 0: 31%|███▏ | 91/291 [00:00<00:02, 82.00it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 102.09it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 118.08it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 131.97it/s] Loading 0: 58%|█████▊ | 170/291 [00:01<00:00, 150.19it/s] Loading 0: 65%|██████▍ | 188/291 [00:01<00:01, 87.20it/s] Loading 0: 71%|███████ | 206/291 [00:01<00:00, 102.18it/s] Loading 0: 78%|███████▊ | 228/291 [00:01<00:00, 122.55it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 135.39it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 144.49it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 12.15it/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-v4-mkmlizer: quantized model in 18.252s
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: Processed model cgato/TheSpice-L3-8b-v0.3.2-Base in 40.781s
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: creating bucket guanaco-mkml-models
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thespice-l3-8b-v0-3216-v4
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thespice-l3-8b-v0-3216-v4/config.json
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thespice-l3-8b-v0-3216-v4/special_tokens_map.json
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thespice-l3-8b-v0-3216-v4/tokenizer_config.json
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thespice-l3-8b-v0-3216-v4/tokenizer.json
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thespice-l3-8b-v0-3216-v4/flywheel_model.0.safetensors
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thespice-l3-8b-v0-3216-v4-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-v4-mkmlizer: warnings.warn(
cgato-thespice-l3-8b-v0-3216-v4-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-v4-mkmlizer: warnings.warn(
cgato-thespice-l3-8b-v0-3216-v4-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-v4-mkmlizer: warnings.warn(
cgato-thespice-l3-8b-v0-3216-v4-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-v4-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: Saving duration: 0.269s
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.184s
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: creating bucket guanaco-reward-models
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thespice-l3-8b-v0-3216-v4_reward
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thespice-l3-8b-v0-3216-v4_reward/config.json
cgato-thespice-l3-8b-v0-3216-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thespice-l3-8b-v0-3216-v4_reward/reward.tensors
Job cgato-thespice-l3-8b-v0-3216-v4-mkmlizer completed after 74.37s with status: succeeded
Stopping job with name cgato-thespice-l3-8b-v0-3216-v4-mkmlizer
Pipeline stage MKMLizer completed in 78.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thespice-l3-8b-v0-3216-v4
Waiting for inference service cgato-thespice-l3-8b-v0-3216-v4 to be ready
Inference service cgato-thespice-l3-8b-v0-3216-v4 ready after 30.184056520462036s
Pipeline stage ISVCDeployer completed in 38.49s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1131837368011475s
Received healthy response to inference request in 1.296433925628662s
Received healthy response to inference request in 1.2423062324523926s
Received healthy response to inference request in 7.258301019668579s
Received healthy response to inference request in 1.2132339477539062s
5 requests
0 failed requests
5th percentile: 1.2190484046936034
10th percentile: 1.2248628616333008
20th percentile: 1.2364917755126954
30th percentile: 1.2531317710876464
40th percentile: 1.2747828483581543
50th percentile: 1.296433925628662
60th percentile: 1.6231338500976562
70th percentile: 1.9498337745666503
80th percentile: 3.1422071933746345
90th percentile: 5.200254106521607
95th percentile: 6.229277563095092
99th percentile: 7.0524963283538815
mean time: 2.6246917724609373
Pipeline stage StressChecker completed in 13.77s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cgato-thespice-l3-8b-v0-_3216_v4 status is now deployed due to DeploymentManager action
cgato-thespice-l3-8b-v0-_3216_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-thespice-l3-8b-v0-_3216_v4
Running pipeline stage ISVCDeleter
Checking if service cgato-thespice-l3-8b-v0-3216-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 1.89s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-thespice-l3-8b-v0-3216-v4/config.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-l3-8b-v0-3216-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-thespice-l3-8b-v0-3216-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-l3-8b-v0-3216-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-thespice-l3-8b-v0-3216-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-thespice-l3-8b-v0-3216-v4_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-l3-8b-v0-3216-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-thespice-l3-8b-v0-3216-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-thespice-l3-8b-v0-3216-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-thespice-l3-8b-v0-3216-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-thespice-l3-8b-v0-3216-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-thespice-l3-8b-v0-3216-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.35s
cgato-thespice-l3-8b-v0-_3216_v4 status is now torndown due to DeploymentManager action