chaser-cz-qlora-out

developer_uid: chace9580

submission_id: chaser-cz-qlora-out_v6

model_name: chaser-cz-qlora-out_v6

model_group: Chaser-cz/qlora-out

status: torndown

timestamp: 2024-07-11T00:39:03+00:00

num_battles: 29380

num_wins: 13751

celo_rating: 1162.91

family_friendly_score: 0.0

submission_type: basic

model_repo: Chaser-cz/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-qlora-out_v6

is_internal_developer: False

language_model: Chaser-cz/qlora-out

model_size: 7B

ranking_group: single

us_pacific_date: 2024-07-10

win_ratio: 0.46803948264125256

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-qlora-out-v6-mkmlizer
Waiting for job on chaser-cz-qlora-out-v6-mkmlizer to finish
chaser-cz-qlora-out-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaser-cz-qlora-out-v6-mkmlizer: ║     _____            __           __                                ║
chaser-cz-qlora-out-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaser-cz-qlora-out-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaser-cz-qlora-out-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaser-cz-qlora-out-v6-mkmlizer: ║       /___/                                                         ║
chaser-cz-qlora-out-v6-mkmlizer: ║                                                                     ║
chaser-cz-qlora-out-v6-mkmlizer: ║  Version: 0.8.14                                                    ║
chaser-cz-qlora-out-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaser-cz-qlora-out-v6-mkmlizer: ║  https://mk1.ai                                                     ║
chaser-cz-qlora-out-v6-mkmlizer: ║                                                                     ║
chaser-cz-qlora-out-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
chaser-cz-qlora-out-v6-mkmlizer: ║  belonging to:                                                      ║
chaser-cz-qlora-out-v6-mkmlizer: ║                                                                     ║
chaser-cz-qlora-out-v6-mkmlizer: ║  Chai Research Corp.                                                ║
chaser-cz-qlora-out-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaser-cz-qlora-out-v6-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaser-cz-qlora-out-v6-mkmlizer: ║                                                                     ║
chaser-cz-qlora-out-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaser-cz-qlora-out-v6-mkmlizer: Downloaded to shared memory in 29.066s
chaser-cz-qlora-out-v6-mkmlizer: quantizing model to /dev/shm/model_cache
chaser-cz-qlora-out-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaser-cz-qlora-out-v6-mkmlizer: quantized model in 19.056s
chaser-cz-qlora-out-v6-mkmlizer: Processed model Chaser-cz/qlora-out in 48.122s
chaser-cz-qlora-out-v6-mkmlizer: creating bucket guanaco-mkml-models
chaser-cz-qlora-out-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaser-cz-qlora-out-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaser-cz-qlora-out-v6
chaser-cz-qlora-out-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaser-cz-qlora-out-v6/config.json
chaser-cz-qlora-out-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaser-cz-qlora-out-v6/tokenizer_config.json
chaser-cz-qlora-out-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaser-cz-qlora-out-v6/special_tokens_map.json
chaser-cz-qlora-out-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaser-cz-qlora-out-v6/tokenizer.model
chaser-cz-qlora-out-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaser-cz-qlora-out-v6/tokenizer.json
chaser-cz-qlora-out-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaser-cz-qlora-out-v6/flywheel_model.0.safetensors
chaser-cz-qlora-out-v6-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:02, 70.92it/s]
Loading 0:  70%|███████   | 204/291 [00:02<00:01, 79.33it/s]
Loading 0: 100%|██████████| 291/291 [00:04<00:00, 64.35it/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-qlora-out-v6-mkmlizer:   warnings.warn(
chaser-cz-qlora-out-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
chaser-cz-qlora-out-v6-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-qlora-out-v6-mkmlizer:   warnings.warn(
chaser-cz-qlora-out-v6-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-qlora-out-v6-mkmlizer:   warnings.warn(
chaser-cz-qlora-out-v6-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-qlora-out-v6-mkmlizer:   warnings.warn(
chaser-cz-qlora-out-v6-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-qlora-out-v6-mkmlizer:   return self.fget.__get__(instance, owner)()
chaser-cz-qlora-out-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaser-cz-qlora-out-v6-mkmlizer: Saving duration: 0.516s
chaser-cz-qlora-out-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.765s
chaser-cz-qlora-out-v6-mkmlizer: creating bucket guanaco-reward-models
chaser-cz-qlora-out-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaser-cz-qlora-out-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaser-cz-qlora-out-v6_reward
chaser-cz-qlora-out-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaser-cz-qlora-out-v6_reward/special_tokens_map.json
chaser-cz-qlora-out-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaser-cz-qlora-out-v6_reward/config.json
chaser-cz-qlora-out-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaser-cz-qlora-out-v6_reward/tokenizer_config.json
chaser-cz-qlora-out-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaser-cz-qlora-out-v6_reward/merges.txt
chaser-cz-qlora-out-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaser-cz-qlora-out-v6_reward/vocab.json
chaser-cz-qlora-out-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaser-cz-qlora-out-v6_reward/tokenizer.json
chaser-cz-qlora-out-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaser-cz-qlora-out-v6_reward/reward.tensors
Job chaser-cz-qlora-out-v6-mkmlizer completed after 83.85s with status: succeeded
Stopping job with name chaser-cz-qlora-out-v6-mkmlizer
Pipeline stage MKMLizer completed in 85.25s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service chaser-cz-qlora-out-v6
Waiting for inference service chaser-cz-qlora-out-v6 to be ready
Inference service chaser-cz-qlora-out-v6 ready after 30.16298222541809s
Pipeline stage ISVCDeployer completed in 37.36s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9757986068725586s
Received healthy response to inference request in 1.171738624572754s
Received healthy response to inference request in 1.1907212734222412s
Received healthy response to inference request in 1.1846461296081543s
Received healthy response to inference request in 1.1623013019561768s
5 requests
0 failed requests
5th percentile: 1.164188766479492
10th percentile: 1.1660762310028077
20th percentile: 1.1698511600494386
30th percentile: 1.174320125579834
40th percentile: 1.179483127593994
50th percentile: 1.1846461296081543
60th percentile: 1.1870761871337892
70th percentile: 1.1895062446594238
80th percentile: 1.3477367401123048
90th percentile: 1.6617676734924318
95th percentile: 1.818783140182495
99th percentile: 1.9443955135345459
mean time: 1.337041187286377
Pipeline stage StressChecker completed in 7.58s
chaser-cz-qlora-out_v6 status is now deployed due to DeploymentManager action
chaser-cz-qlora-out_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaser-cz-qlora-out_v6
Running pipeline stage ISVCDeleter
Checking if service chaser-cz-qlora-out-v6 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.95s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaser-cz-qlora-out-v6/config.json from bucket guanaco-mkml-models
Deleting key chaser-cz-qlora-out-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaser-cz-qlora-out-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaser-cz-qlora-out-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaser-cz-qlora-out-v6/tokenizer.model from bucket guanaco-mkml-models
Deleting key chaser-cz-qlora-out-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaser-cz-qlora-out-v6_reward/config.json from bucket guanaco-reward-models
Deleting key chaser-cz-qlora-out-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaser-cz-qlora-out-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaser-cz-qlora-out-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaser-cz-qlora-out-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaser-cz-qlora-out-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaser-cz-qlora-out-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.74s
chaser-cz-qlora-out_v6 status is now torndown due to DeploymentManager action