submission_id: cgato-thesalt-rp-l3-8b-v0-3-2_v8
developer_uid: c.gato
best_of: 16
celo_rating: 1197.75
display_name: cgato-thesalt-rp-l3-8b-v0-3-2_v8
family_friendly_score: 0.0
formatter: {'memory_template': '<|im_start|>system\n{memory}\n', 'prompt_template': '{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': 1.0, 'top_p': 1.0, '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/TheSalt-RP-L3-8b-v0.3.2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cgato/TheSalt-RP-L3-8b-v
model_name: cgato-thesalt-rp-l3-8b-v0-3-2_v8
model_num_parameters: 8030294016.0
model_repo: cgato/TheSalt-RP-L3-8b-v0.3.2
model_size: 8B
num_battles: 18280
num_wins: 9589
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: 2024-06-19T19:43:26+00:00
us_pacific_date: 2024-06-19
win_ratio: 0.524562363238512
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer to finish
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: Downloaded to shared memory in 27.032s
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 126.47it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 147.13it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 151.06it/s] Loading 0: 22%|██▏ | 64/291 [00:00<00:01, 151.55it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 147.40it/s] Loading 0: 33%|███▎ | 95/291 [00:01<00:02, 68.93it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 86.30it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 102.58it/s] Loading 0: 49%|████▉ | 144/291 [00:01<00:01, 112.82it/s] Loading 0: 55%|█████▍ | 159/291 [00:01<00:01, 119.69it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 136.13it/s] Loading 0: 67%|██████▋ | 195/291 [00:01<00:01, 75.48it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:00, 89.05it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 103.75it/s] Loading 0: 84%|████████▎ | 243/291 [00:02<00:00, 113.09it/s] Loading 0: 89%|████████▊ | 258/291 [00:02<00:00, 119.42it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 128.82it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 9.83it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: quantized model in 19.141s
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v8
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v8/config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v8/special_tokens_map.json
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v8/tokenizer_config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v8/tokenizer.json
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v8/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-v0-3-2-v8-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-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-v0-3-2-v8-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-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-v0-3-2-v8-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-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: Saving duration: 0.290s
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 10.269s
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v8_reward
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v8_reward/config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v8_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v8_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v8_reward/merges.txt
cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v8_reward/vocab.json
Job cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer completed after 92.9s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-v0-3-2-v8-mkmlizer
Pipeline stage MKMLizer completed in 97.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-v0-3-2-v8
Waiting for inference service cgato-thesalt-rp-l3-8b-v0-3-2-v8 to be ready
Inference service cgato-thesalt-rp-l3-8b-v0-3-2-v8 ready after 50.70990610122681s
Pipeline stage ISVCDeployer completed in 58.82s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.973996877670288s
Received healthy response to inference request in 1.0284805297851562s
Received healthy response to inference request in 1.026904821395874s
Received healthy response to inference request in 1.0368316173553467s
Received healthy response to inference request in 1.0014352798461914s
5 requests
0 failed requests
5th percentile: 1.006529188156128
10th percentile: 1.0116230964660644
20th percentile: 1.0218109130859374
30th percentile: 1.0272199630737304
40th percentile: 1.0278502464294434
50th percentile: 1.0284805297851562
60th percentile: 1.0318209648132324
70th percentile: 1.0351613998413085
80th percentile: 1.2242646694183352
90th percentile: 1.5991307735443117
95th percentile: 1.7865638256072995
99th percentile: 1.9365102672576904
mean time: 1.2135298252105713
Pipeline stage StressChecker completed in 6.67s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cgato-thesalt-rp-l3-8b-v0-3-2_v8 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-v0-3-2_v8 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-thesalt-rp-l3-8b-v0-3-2_v8
Running pipeline stage ISVCDeleter
Checking if service cgato-thesalt-rp-l3-8b-v0-3-2-v8 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.28s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-thesalt-rp-l3-8b-v0-3-2-v8/config.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-v0-3-2-v8/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-v0-3-2-v8/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-v0-3-2-v8/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-v0-3-2-v8/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-thesalt-rp-l3-8b-v0-3-2-v8_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-v0-3-2-v8_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-v0-3-2-v8_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-v0-3-2-v8_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-v0-3-2-v8_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-v0-3-2-v8_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-v0-3-2-v8_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.23s
cgato-thesalt-rp-l3-8b-v0-3-2_v8 status is now torndown due to DeploymentManager action