chaser-cz-sharegpt-qlora-out

developer_uid: chace9580

submission_id: chaser-cz-sharegpt-qlora-out_v1

model_name: chaser-cz-sharegpt-qlora-out_v1

model_group: Chaser-cz/sharegpt-qlora

status: torndown

timestamp: 2024-07-06T06:11:20+00:00

num_battles: 36236

num_wins: 17421

celo_rating: 1170.15

family_friendly_score: 0.0

submission_type: basic

model_repo: Chaser-cz/sharegpt-qlora-out

model_architecture: MistralForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 7241732096.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: chaser-cz-sharegpt-qlora-out_v1

is_internal_developer: False

language_model: Chaser-cz/sharegpt-qlora-out

model_size: 7B

ranking_group: single

us_pacific_date: 2024-07-05

win_ratio: 0.4807649850976929

generation_params: {'temperature': 1.0, 'top_p': 1.0, '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': "{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}

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': False, 'user_template': '{user_name}: {message}\n'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name chaser-cz-sharegpt-qlora-out-v1-mkmlizer
Waiting for job on chaser-cz-sharegpt-qlora-out-v1-mkmlizer to finish
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║     _____            __           __                                ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║       /___/                                                         ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║                                                                     ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║                                                                     ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║  belonging to:                                                      ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║                                                                     ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ║                                                                     ║
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: Downloaded to shared memory in 26.624s
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: quantizing model to /dev/shm/model_cache
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: quantized model in 15.501s
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: Processed model Chaser-cz/sharegpt-qlora-out in 42.126s
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: creating bucket guanaco-mkml-models
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaser-cz-sharegpt-qlora-out-v1
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaser-cz-sharegpt-qlora-out-v1/tokenizer_config.json
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaser-cz-sharegpt-qlora-out-v1/special_tokens_map.json
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaser-cz-sharegpt-qlora-out-v1/tokenizer.model
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaser-cz-sharegpt-qlora-out-v1/tokenizer.json
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaser-cz-sharegpt-qlora-out-v1/config.json
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaser-cz-sharegpt-qlora-out-v1/flywheel_model.0.safetensors
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:02, 80.08it/s]
Loading 0:  70%|███████   | 204/291 [00:02<00:00, 89.48it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 76.42it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaser-cz-sharegpt-qlora-out-v1-mkmlizer:   warnings.warn(
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
chaser-cz-sharegpt-qlora-out-v1-mkmlizer:   warnings.warn(
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaser-cz-sharegpt-qlora-out-v1-mkmlizer:   warnings.warn(
chaser-cz-sharegpt-qlora-out-v1-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.
chaser-cz-sharegpt-qlora-out-v1-mkmlizer:   warnings.warn(
chaser-cz-sharegpt-qlora-out-v1-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()
chaser-cz-sharegpt-qlora-out-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: Saving duration: 0.405s
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.624s
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: creating bucket guanaco-reward-models
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v1_reward
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v1_reward/merges.txt
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v1_reward/config.json
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v1_reward/tokenizer_config.json
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v1_reward/special_tokens_map.json
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v1_reward/vocab.json
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v1_reward/tokenizer.json
chaser-cz-sharegpt-qlora-out-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaser-cz-sharegpt-qlora-out-v1_reward/reward.tensors
Job chaser-cz-sharegpt-qlora-out-v1-mkmlizer completed after 83.35s with status: succeeded
Stopping job with name chaser-cz-sharegpt-qlora-out-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.12s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service chaser-cz-sharegpt-qlora-out-v1
Waiting for inference service chaser-cz-sharegpt-qlora-out-v1 to be ready
Failed to get response for submission blend_joreb_2024-07-04: ('http://mistralai-mixtral-8x7b-3473-v61-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: connection timeout')
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v61: ('http://mistralai-mixtral-8x7b-3473-v61-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: connection timeout')
Inference service chaser-cz-sharegpt-qlora-out-v1 ready after 50.20449638366699s
Pipeline stage ISVCDeployer completed in 56.85s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.002453327178955s
Received healthy response to inference request in 1.1811025142669678s
Received healthy response to inference request in 1.2207021713256836s
Received healthy response to inference request in 1.201239824295044s
Received healthy response to inference request in 1.1965999603271484s
5 requests
0 failed requests
5th percentile: 1.184202003479004
10th percentile: 1.1873014926910401
20th percentile: 1.1935004711151123
30th percentile: 1.1975279331207276
40th percentile: 1.1993838787078857
50th percentile: 1.201239824295044
60th percentile: 1.2090247631073
70th percentile: 1.2168097019195556
80th percentile: 1.377052402496338
90th percentile: 1.6897528648376465
95th percentile: 1.8461030960083007
99th percentile: 1.9711832809448242
mean time: 1.3604195594787598
Pipeline stage StressChecker completed in 7.43s
chaser-cz-sharegpt-qlora-out_v1 status is now deployed due to DeploymentManager action
chaser-cz-sharegpt-qlora-out_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaser-cz-sharegpt-qlora-out_v1
Running pipeline stage ISVCDeleter
Checking if service chaser-cz-sharegpt-qlora-out-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 7.68s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaser-cz-sharegpt-qlora-out-v1/config.json from bucket guanaco-mkml-models
Deleting key chaser-cz-sharegpt-qlora-out-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaser-cz-sharegpt-qlora-out-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaser-cz-sharegpt-qlora-out-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaser-cz-sharegpt-qlora-out-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key chaser-cz-sharegpt-qlora-out-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaser-cz-sharegpt-qlora-out-v1_reward/config.json from bucket guanaco-reward-models
Deleting key chaser-cz-sharegpt-qlora-out-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaser-cz-sharegpt-qlora-out-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaser-cz-sharegpt-qlora-out-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaser-cz-sharegpt-qlora-out-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaser-cz-sharegpt-qlora-out-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaser-cz-sharegpt-qlora-out-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.91s
chaser-cz-sharegpt-qlora-out_v1 status is now torndown due to DeploymentManager action