developer_uid: shiroe40
submission_id: cycy233-l3-be-v0-c3_v1
model_name: auto
model_group: cycy233/L3-be-v0-c3
status: torndown
timestamp: 2024-07-18T03:31:29+00:00
num_battles: 15841
num_wins: 9053
celo_rating: 1240.65
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-be-v0-c3
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: auto
is_internal_developer: False
language_model: cycy233/L3-be-v0-c3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-17
win_ratio: 0.5714916987563916
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
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}
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 cycy233-l3-be-v0-c3-v1-mkmlizer
Waiting for job on cycy233-l3-be-v0-c3-v1-mkmlizer to finish
cycy233-l3-be-v0-c3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-be-v0-c3-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║                                                                     ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║  Version: 0.9.5.post3                                               ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║                                                                     ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║                                                                     ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ║                                                                     ║
cycy233-l3-be-v0-c3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-be-v0-c3-v1-mkmlizer: Downloaded to shared memory in 31.654s
cycy233-l3-be-v0-c3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9oyg4fm0, device:0
cycy233-l3-be-v0-c3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-be-v0-c3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:04, 69.36it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:03, 55.49it/s]
Loading 0:  43%|████▎     | 125/291 [00:01<00:01, 85.01it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 53.04it/s]
Loading 0:  89%|████████▉ | 260/291 [00:03<00:00, 89.86it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-be-v0-c3-v1-mkmlizer: quantized model in 30.851s
cycy233-l3-be-v0-c3-v1-mkmlizer: Processed model cycy233/L3-be-v0-c3 in 62.505s
cycy233-l3-be-v0-c3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-be-v0-c3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-be-v0-c3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-be-v0-c3-v1
cycy233-l3-be-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-be-v0-c3-v1/config.json
cycy233-l3-be-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-be-v0-c3-v1/special_tokens_map.json
cycy233-l3-be-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-be-v0-c3-v1/tokenizer_config.json
cycy233-l3-be-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-be-v0-c3-v1/tokenizer.json
cycy233-l3-be-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-be-v0-c3-v1/flywheel_model.0.safetensors
cycy233-l3-be-v0-c3-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-be-v0-c3-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-be-v0-c3-v1-mkmlizer:   warnings.warn(
cycy233-l3-be-v0-c3-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-be-v0-c3-v1-mkmlizer:   warnings.warn(
cycy233-l3-be-v0-c3-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.
cycy233-l3-be-v0-c3-v1-mkmlizer:   warnings.warn(
cycy233-l3-be-v0-c3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-be-v0-c3-v1-mkmlizer: Saving duration: 2.258s
cycy233-l3-be-v0-c3-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 15.235s
cycy233-l3-be-v0-c3-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-be-v0-c3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-be-v0-c3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-be-v0-c3-v1_reward
cycy233-l3-be-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-be-v0-c3-v1_reward/tokenizer_config.json
cycy233-l3-be-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-be-v0-c3-v1_reward/special_tokens_map.json
cycy233-l3-be-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-be-v0-c3-v1_reward/config.json
cycy233-l3-be-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-be-v0-c3-v1_reward/merges.txt
cycy233-l3-be-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-be-v0-c3-v1_reward/vocab.json
cycy233-l3-be-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-be-v0-c3-v1_reward/tokenizer.json
cycy233-l3-be-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-be-v0-c3-v1_reward/reward.tensors
Job cycy233-l3-be-v0-c3-v1-mkmlizer completed after 107.33s with status: succeeded
Stopping job with name cycy233-l3-be-v0-c3-v1-mkmlizer
Pipeline stage MKMLizer completed in 108.80s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-be-v0-c3-v1
Waiting for inference service cycy233-l3-be-v0-c3-v1 to be ready
Inference service cycy233-l3-be-v0-c3-v1 ready after 81.33704280853271s
Pipeline stage ISVCDeployer completed in 83.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.17219877243042s
Failed to get response for submission hastagaras-dirtybu8bl3-r_5954_v3: ('http://hastagaras-dirtybu8bl3-r-5954-v3-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Received healthy response to inference request in 1.4770219326019287s
Received healthy response to inference request in 1.4569954872131348s
Received healthy response to inference request in 1.4227361679077148s
Received healthy response to inference request in 1.482668161392212s
5 requests
0 failed requests
5th percentile: 1.4295880317687988
10th percentile: 1.4364398956298827
20th percentile: 1.4501436233520508
30th percentile: 1.4610007762908936
40th percentile: 1.4690113544464112
50th percentile: 1.4770219326019287
60th percentile: 1.479280424118042
70th percentile: 1.4815389156341552
80th percentile: 1.6205742835998536
90th percentile: 1.8963865280151369
95th percentile: 2.034292650222778
99th percentile: 2.1446175479888914
mean time: 1.6023241043090821
Pipeline stage StressChecker completed in 8.62s
cycy233-l3-be-v0-c3_v1 status is now deployed due to DeploymentManager action
cycy233-l3-be-v0-c3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-be-v0-c3_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-be-v0-c3-v1 is running
Tearing down inference service cycy233-l3-be-v0-c3-v1
Service cycy233-l3-be-v0-c3-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.49s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-be-v0-c3-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-be-v0-c3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-be-v0-c3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-be-v0-c3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-be-v0-c3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-be-v0-c3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-be-v0-c3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-be-v0-c3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-be-v0-c3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-be-v0-c3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-be-v0-c3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-be-v0-c3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.44s
cycy233-l3-be-v0-c3_v1 status is now torndown due to DeploymentManager action