hastagaras-jakal-001

submission_id: hastagaras-jakal-001_v2

developer_uid: Hastagaras

best_of: 8

celo_rating: 1214.52

display_name: hehe

family_friendly_score: 0.0

formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 1.35, 'top_p': 1.0, 'min_p': 0.12, 'top_k': 250, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|eot_id|>', '\n\n', '\nYou:', '\n{bot_name}:', '\n{user_name}:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

is_internal_developer: False

language_model: Hastagaras/Jakal.001

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Hastagaras/Jakal.001

model_name: hehe

model_num_parameters: 8030261248.0

model_repo: Hastagaras/Jakal.001

model_size: 8B

num_battles: 13581

num_wins: 7224

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

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-07-04T03:41:32+00:00

us_pacific_date: 2024-07-03

win_ratio: 0.5319195935498122

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-jakal-001-v2-mkmlizer
Waiting for job on hastagaras-jakal-001-v2-mkmlizer to finish
hastagaras-jakal-001-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jakal-001-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-jakal-001-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-jakal-001-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-jakal-001-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-jakal-001-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-jakal-001-v2-mkmlizer: ║                                                                     ║
hastagaras-jakal-001-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-jakal-001-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-jakal-001-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-jakal-001-v2-mkmlizer: ║                                                                     ║
hastagaras-jakal-001-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-jakal-001-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-jakal-001-v2-mkmlizer: ║                                                                     ║
hastagaras-jakal-001-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-jakal-001-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-jakal-001-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-jakal-001-v2-mkmlizer: ║                                                                     ║
hastagaras-jakal-001-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
hastagaras-jakal-001-v2-mkmlizer: Downloaded to shared memory in 43.738s
hastagaras-jakal-001-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jakal-001-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
hastagaras-jakal-001-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jakal-001-v2/config.json
hastagaras-jakal-001-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jakal-001-v2/tokenizer_config.json
hastagaras-jakal-001-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jakal-001-v2/special_tokens_map.json
hastagaras-jakal-001-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jakal-001-v2/tokenizer.json
hastagaras-jakal-001-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jakal-001-v2/flywheel_model.0.safetensors
hastagaras-jakal-001-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jakal-001-v2-mkmlizer: /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.
hastagaras-jakal-001-v2-mkmlizer:   warnings.warn(
hastagaras-jakal-001-v2-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`.
hastagaras-jakal-001-v2-mkmlizer:   warnings.warn(
hastagaras-jakal-001-v2-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.
hastagaras-jakal-001-v2-mkmlizer:   warnings.warn(
hastagaras-jakal-001-v2-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.
hastagaras-jakal-001-v2-mkmlizer:   warnings.warn(
hastagaras-jakal-001-v2-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()
hastagaras-jakal-001-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-jakal-001-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jakal-001-v2-mkmlizer: Saving duration: 0.405s
hastagaras-jakal-001-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 13.144s
hastagaras-jakal-001-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jakal-001-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jakal-001-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jakal-001-v2_reward
hastagaras-jakal-001-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jakal-001-v2_reward/config.json
hastagaras-jakal-001-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jakal-001-v2_reward/special_tokens_map.json
hastagaras-jakal-001-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jakal-001-v2_reward/tokenizer_config.json
hastagaras-jakal-001-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jakal-001-v2_reward/vocab.json
hastagaras-jakal-001-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jakal-001-v2_reward/merges.txt
hastagaras-jakal-001-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jakal-001-v2_reward/tokenizer.json
hastagaras-jakal-001-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jakal-001-v2_reward/reward.tensors
Job hastagaras-jakal-001-v2-mkmlizer completed after 103.83s with status: succeeded
Stopping job with name hastagaras-jakal-001-v2-mkmlizer
Pipeline stage MKMLizer completed in 104.99s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jakal-001-v2
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Waiting for inference service hastagaras-jakal-001-v2 to be ready
Inference service hastagaras-jakal-001-v2 ready after 40.2439444065094s
Pipeline stage ISVCDeployer completed in 47.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0044310092926025s
Received healthy response to inference request in 1.22365140914917s
Received healthy response to inference request in 1.3116681575775146s
Received healthy response to inference request in 1.2827744483947754s
Received healthy response to inference request in 1.1996304988861084s
5 requests
0 failed requests
5th percentile: 1.2044346809387207
10th percentile: 1.209238862991333
20th percentile: 1.2188472270965576
30th percentile: 1.235476016998291
40th percentile: 1.2591252326965332
50th percentile: 1.2827744483947754
60th percentile: 1.294331932067871
70th percentile: 1.3058894157409668
80th percentile: 1.4502207279205324
90th percentile: 1.7273258686065676
95th percentile: 1.8658784389495848
99th percentile: 1.976720495223999
mean time: 1.4044311046600342
Pipeline stage StressChecker completed in 7.93s
hastagaras-jakal-001_v2 status is now deployed due to DeploymentManager action
hastagaras-jakal-001_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-jakal-001_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-jakal-001-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.84s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-jakal-001-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-jakal-001-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-jakal-001-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-jakal-001-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-jakal-001-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-jakal-001-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-jakal-001-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-jakal-001-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-jakal-001-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-jakal-001-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-jakal-001-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-jakal-001-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.55s
hastagaras-jakal-001_v2 status is now torndown due to DeploymentManager action