developer_uid: shiroe40
submission_id: cycy233-l3-be-v0-c4_v1
model_name: auto
model_group: cycy233/L3-be-v0-c4
status: torndown
timestamp: 2024-07-18T03:31:45+00:00
num_battles: 15747
num_wins: 9049
celo_rating: 1242.63
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-be-v0-c4
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-c4
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-17
win_ratio: 0.5746491395186385
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-c4-v1-mkmlizer
Waiting for job on cycy233-l3-be-v0-c4-v1-mkmlizer to finish
cycy233-l3-be-v0-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ /___/ ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ Version: 0.9.5.post3 ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-be-v0-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-be-v0-c4-v1-mkmlizer: Downloaded to shared memory in 30.663s
cycy233-l3-be-v0-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp379o2wcu, device:0
cycy233-l3-be-v0-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-be-v0-c4-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 59.20it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 70.16it/s] Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 101.93it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-be-v0-c4-v1-mkmlizer: quantized model in 29.161s
cycy233-l3-be-v0-c4-v1-mkmlizer: Processed model cycy233/L3-be-v0-c4 in 59.824s
cycy233-l3-be-v0-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-be-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-be-v0-c4-v1/flywheel_model.0.safetensors
cycy233-l3-be-v0-c4-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-be-v0-c4-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-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-be-v0-c4-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-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-be-v0-c4-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-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-be-v0-c4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-be-v0-c4-v1-mkmlizer: Saving duration: 2.230s
cycy233-l3-be-v0-c4-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 13.165s
cycy233-l3-be-v0-c4-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-be-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-be-v0-c4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-be-v0-c4-v1_reward
cycy233-l3-be-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-be-v0-c4-v1_reward/config.json
cycy233-l3-be-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-be-v0-c4-v1_reward/tokenizer_config.json
cycy233-l3-be-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-be-v0-c4-v1_reward/special_tokens_map.json
cycy233-l3-be-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-be-v0-c4-v1_reward/vocab.json
cycy233-l3-be-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-be-v0-c4-v1_reward/merges.txt
cycy233-l3-be-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-be-v0-c4-v1_reward/tokenizer.json
cycy233-l3-be-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-be-v0-c4-v1_reward/reward.tensors
Job cycy233-l3-be-v0-c4-v1-mkmlizer completed after 108.11s with status: succeeded
Stopping job with name cycy233-l3-be-v0-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 109.15s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-be-v0-c4-v1
Waiting for inference service cycy233-l3-be-v0-c4-v1 to be ready
Inference service cycy233-l3-be-v0-c4-v1 ready after 40.675679206848145s
Pipeline stage ISVCDeployer completed in 42.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2819435596466064s
Received healthy response to inference request in 1.5080561637878418s
Received healthy response to inference request in 1.446765661239624s
Received healthy response to inference request in 1.447648286819458s
Received healthy response to inference request in 1.5144920349121094s
5 requests
0 failed requests
5th percentile: 1.446942186355591
10th percentile: 1.4471187114715576
20th percentile: 1.4474717617034911
30th percentile: 1.4597298622131347
40th percentile: 1.4838930130004884
50th percentile: 1.5080561637878418
60th percentile: 1.5106305122375487
70th percentile: 1.513204860687256
80th percentile: 1.667982339859009
90th percentile: 1.9749629497528076
95th percentile: 2.128453254699707
99th percentile: 2.2512454986572266
mean time: 1.6397811412811278
Pipeline stage StressChecker completed in 9.05s
cycy233-l3-be-v0-c4_v1 status is now deployed due to DeploymentManager action
cycy233-l3-be-v0-c4_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-be-v0-c4_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-be-v0-c4-v1 is running
Tearing down inference service cycy233-l3-be-v0-c4-v1
Service cycy233-l3-be-v0-c4-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.56s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-be-v0-c4-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-be-v0-c4-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-be-v0-c4-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-be-v0-c4-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-be-v0-c4-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-be-v0-c4-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-be-v0-c4-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-be-v0-c4-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-be-v0-c4-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-be-v0-c4-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-be-v0-c4-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-be-v0-c4-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.49s
cycy233-l3-be-v0-c4_v1 status is now torndown due to DeploymentManager action