submission_id: beaverai-mistral-doryv2-12b_v1
developer_uid: Azazelle
best_of: 4
celo_rating: 1204.26
display_name: mistral-doryV2-12b
family_friendly_score: 0.0
formatter: {'memory_template': "### System:\\\n{bot_name}'s Persona: {memory}\\\n\\\n", 'prompt_template': '{prompt}</s>', 'bot_template': '### Response:\\\n{bot_name}: {message}</s>\\\n\\\n', 'user_template': '### Query: {user_name}: {message}\\\n\\\n', 'response_template': '### Response:\\\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.7, 'top_p': 1.0, 'min_p': 0.07, 'top_k': 1024, 'presence_penalty': 0.03, 'frequency_penalty': 0.01, 'stopping_words': ['\n', '\n\n', 'You:'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 1024}
is_internal_developer: False
language_model: BeaverAI/mistral-doryV2-12b
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: BeaverAI/mistral-doryV2-
model_name: mistral-doryV2-12b
model_num_parameters: 12772070400.0
model_repo: BeaverAI/mistral-doryV2-12b
model_size: 13B
num_battles: 35136
num_wins: 19705
ranking_group: single
reward_formatter: {'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-28T19:07:22+00:00
us_pacific_date: 2024-07-28
win_ratio: 0.560820810564663
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name beaverai-mistral-doryv2-12b-v1-mkmlizer
Waiting for job on beaverai-mistral-doryv2-12b-v1-mkmlizer to finish
Failed to get response for submission sao10k-hydrochoerus-12b-v1-s1_v3: ('http://sao10k-hydrochoerus-12b-v1-s1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
beaverai-mistral-doryv2-12b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ _____ __ __ ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ /___/ ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ Version: 0.9.7 ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ https://mk1.ai ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ belonging to: ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ Chai Research Corp. ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ║ ║
beaverai-mistral-doryv2-12b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
beaverai-mistral-doryv2-12b-v1-mkmlizer: Downloaded to shared memory in 37.911s
beaverai-mistral-doryv2-12b-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptnz08djr, device:0
beaverai-mistral-doryv2-12b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
beaverai-mistral-doryv2-12b-v1-mkmlizer: quantized model in 35.701s
beaverai-mistral-doryv2-12b-v1-mkmlizer: Processed model BeaverAI/mistral-doryV2-12b in 73.612s
beaverai-mistral-doryv2-12b-v1-mkmlizer: creating bucket guanaco-mkml-models
beaverai-mistral-doryv2-12b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
beaverai-mistral-doryv2-12b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/beaverai-mistral-doryv2-12b-v1
beaverai-mistral-doryv2-12b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/beaverai-mistral-doryv2-12b-v1/config.json
beaverai-mistral-doryv2-12b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/beaverai-mistral-doryv2-12b-v1/special_tokens_map.json
beaverai-mistral-doryv2-12b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/beaverai-mistral-doryv2-12b-v1/tokenizer_config.json
beaverai-mistral-doryv2-12b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/beaverai-mistral-doryv2-12b-v1/tokenizer.json
beaverai-mistral-doryv2-12b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/beaverai-mistral-doryv2-12b-v1/flywheel_model.0.safetensors
beaverai-mistral-doryv2-12b-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
beaverai-mistral-doryv2-12b-v1-mkmlizer: warnings.warn(
beaverai-mistral-doryv2-12b-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
beaverai-mistral-doryv2-12b-v1-mkmlizer: warnings.warn(
beaverai-mistral-doryv2-12b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
beaverai-mistral-doryv2-12b-v1-mkmlizer: Saving duration: 0.325s
beaverai-mistral-doryv2-12b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.212s
beaverai-mistral-doryv2-12b-v1-mkmlizer: creating bucket guanaco-reward-models
beaverai-mistral-doryv2-12b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
beaverai-mistral-doryv2-12b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/beaverai-mistral-doryv2-12b-v1_reward
beaverai-mistral-doryv2-12b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/beaverai-mistral-doryv2-12b-v1_reward/config.json
beaverai-mistral-doryv2-12b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/beaverai-mistral-doryv2-12b-v1_reward/special_tokens_map.json
beaverai-mistral-doryv2-12b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/beaverai-mistral-doryv2-12b-v1_reward/tokenizer_config.json
beaverai-mistral-doryv2-12b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/beaverai-mistral-doryv2-12b-v1_reward/merges.txt
beaverai-mistral-doryv2-12b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/beaverai-mistral-doryv2-12b-v1_reward/vocab.json
beaverai-mistral-doryv2-12b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/beaverai-mistral-doryv2-12b-v1_reward/tokenizer.json
beaverai-mistral-doryv2-12b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/beaverai-mistral-doryv2-12b-v1_reward/reward.tensors
Job beaverai-mistral-doryv2-12b-v1-mkmlizer completed after 116.36s with status: succeeded
Stopping job with name beaverai-mistral-doryv2-12b-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service beaverai-mistral-doryv2-12b-v1
Waiting for inference service beaverai-mistral-doryv2-12b-v1 to be ready
Failed to get response for submission sao10k-hydrochoerus-12b-v1-s1_v3: ('http://sao10k-hydrochoerus-12b-v1-s1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission sao10k-hydrochoerus-12b-v1-s1_v3: ('http://sao10k-hydrochoerus-12b-v1-s1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service beaverai-mistral-doryv2-12b-v1 ready after 100.67150926589966s
Pipeline stage ISVCDeployer completed in 102.64s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4693245887756348s
Received healthy response to inference request in 1.5844652652740479s
Received healthy response to inference request in 1.3365426063537598s
Received healthy response to inference request in 1.611412763595581s
Received healthy response to inference request in 1.637010097503662s
5 requests
0 failed requests
5th percentile: 1.3861271381378173
10th percentile: 1.435711669921875
20th percentile: 1.5348807334899903
30th percentile: 1.5898547649383545
40th percentile: 1.6006337642669677
50th percentile: 1.611412763595581
60th percentile: 1.6216516971588135
70th percentile: 1.631890630722046
80th percentile: 1.8034729957580569
90th percentile: 2.1363987922668457
95th percentile: 2.3028616905212402
99th percentile: 2.436032009124756
mean time: 1.7277510643005372
Pipeline stage StressChecker completed in 9.30s
beaverai-mistral-doryv2-12b_v1 status is now deployed due to DeploymentManager action
beaverai-mistral-doryv2-12b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of beaverai-mistral-doryv2-12b_v1
Running pipeline stage ISVCDeleter
Checking if service beaverai-mistral-doryv2-12b-v1 is running
Tearing down inference service beaverai-mistral-doryv2-12b-v1
Service beaverai-mistral-doryv2-12b-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.91s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key beaverai-mistral-doryv2-12b-v1/config.json from bucket guanaco-mkml-models
Deleting key beaverai-mistral-doryv2-12b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key beaverai-mistral-doryv2-12b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key beaverai-mistral-doryv2-12b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key beaverai-mistral-doryv2-12b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key beaverai-mistral-doryv2-12b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key beaverai-mistral-doryv2-12b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key beaverai-mistral-doryv2-12b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key beaverai-mistral-doryv2-12b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key beaverai-mistral-doryv2-12b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key beaverai-mistral-doryv2-12b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key beaverai-mistral-doryv2-12b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.88s
beaverai-mistral-doryv2-12b_v1 status is now torndown due to DeploymentManager action