developer_uid: shiroe40
submission_id: cycy233-l3-e-v1-c1_v1
model_name: auto
model_group: cycy233/L3-e-v1-c1
status: torndown
timestamp: 2024-07-18T03:11:35+00:00
num_battles: 16075
num_wins: 7554
celo_rating: 1167.79
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-e-v1-c1
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-e-v1-c1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-17
win_ratio: 0.4699222395023328
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-e-v1-c1-v1-mkmlizer
Waiting for job on cycy233-l3-e-v1-c1-v1-mkmlizer to finish
cycy233-l3-e-v1-c1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ /___/ ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ Version: 0.9.5.post3 ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ║ ║
cycy233-l3-e-v1-c1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
cycy233-l3-e-v1-c1-v1-mkmlizer: Downloaded to shared memory in 34.798s
cycy233-l3-e-v1-c1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb3llqzzg, device:0
cycy233-l3-e-v1-c1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v1-c1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 116.52it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 109.66it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 124.75it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:01, 121.86it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 127.00it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:01, 122.76it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:03, 58.13it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 65.29it/s] Loading 0: 40%|███▉ | 116/291 [00:01<00:02, 77.24it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 87.34it/s] Loading 0: 49%|████▉ | 143/291 [00:01<00:01, 96.64it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 104.21it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 103.97it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:01, 108.80it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 54.44it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 59.51it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:01, 64.18it/s] Loading 0: 76%|███████▌ | 221/291 [00:02<00:01, 68.73it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 86.00it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 89.50it/s] Loading 0: 91%|█████████ | 264/291 [00:03<00:00, 104.06it/s] Loading 0: 95%|█████████▍| 276/291 [00:03<00:00, 104.15it/s] Loading 0: 99%|█████████▉| 288/291 [00:10<00:00, 5.69it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-e-v1-c1-v1-mkmlizer: quantized model in 30.036s
cycy233-l3-e-v1-c1-v1-mkmlizer: Processed model cycy233/L3-e-v1-c1 in 64.834s
cycy233-l3-e-v1-c1-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v1-c1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v1-c1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v1-c1-v1
cycy233-l3-e-v1-c1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v1-c1-v1/config.json
cycy233-l3-e-v1-c1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v1-c1-v1/special_tokens_map.json
cycy233-l3-e-v1-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v1-c1-v1/tokenizer_config.json
cycy233-l3-e-v1-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v1-c1-v1/tokenizer.json
cycy233-l3-e-v1-c1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v1-c1-v1/flywheel_model.0.safetensors
cycy233-l3-e-v1-c1-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v1-c1-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-e-v1-c1-v1-mkmlizer: warnings.warn(
cycy233-l3-e-v1-c1-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-e-v1-c1-v1-mkmlizer: warnings.warn(
cycy233-l3-e-v1-c1-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-e-v1-c1-v1-mkmlizer: warnings.warn(
cycy233-l3-e-v1-c1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v1-c1-v1-mkmlizer: Saving duration: 2.315s
cycy233-l3-e-v1-c1-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 13.466s
cycy233-l3-e-v1-c1-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v1-c1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v1-c1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v1-c1-v1_reward
cycy233-l3-e-v1-c1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v1-c1-v1_reward/config.json
cycy233-l3-e-v1-c1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v1-c1-v1_reward/special_tokens_map.json
cycy233-l3-e-v1-c1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v1-c1-v1_reward/tokenizer_config.json
cycy233-l3-e-v1-c1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v1-c1-v1_reward/merges.txt
cycy233-l3-e-v1-c1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v1-c1-v1_reward/vocab.json
cycy233-l3-e-v1-c1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v1-c1-v1_reward/tokenizer.json
cycy233-l3-e-v1-c1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v1-c1-v1_reward/reward.tensors
Job cycy233-l3-e-v1-c1-v1-mkmlizer completed after 127.1s with status: succeeded
Stopping job with name cycy233-l3-e-v1-c1-v1-mkmlizer
Pipeline stage MKMLizer completed in 128.33s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v1-c1-v1
Waiting for inference service cycy233-l3-e-v1-c1-v1 to be ready
Inference service cycy233-l3-e-v1-c1-v1 ready after 91.44410061836243s
Pipeline stage ISVCDeployer completed in 93.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2858986854553223s
Received healthy response to inference request in 1.4738917350769043s
Received healthy response to inference request in 1.459320068359375s
Received healthy response to inference request in 1.3709301948547363s
Received healthy response to inference request in 1.4887988567352295s
5 requests
0 failed requests
5th percentile: 1.388608169555664
10th percentile: 1.4062861442565917
20th percentile: 1.4416420936584473
30th percentile: 1.4622344017028808
40th percentile: 1.4680630683898925
50th percentile: 1.4738917350769043
60th percentile: 1.4798545837402344
70th percentile: 1.4858174324035645
80th percentile: 1.6482188224792482
90th percentile: 1.9670587539672852
95th percentile: 2.1264787197113035
99th percentile: 2.2540146923065185
mean time: 1.6157679080963134
Pipeline stage StressChecker completed in 8.91s
cycy233-l3-e-v1-c1_v1 status is now deployed due to DeploymentManager action
cycy233-l3-e-v1-c1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v1-c1_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v1-c1-v1 is running
Tearing down inference service cycy233-l3-e-v1-c1-v1
Service cycy233-l3-e-v1-c1-v1 has been torndown
Pipeline stage ISVCDeleter completed in 5.38s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v1-c1-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v1-c1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v1-c1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v1-c1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v1-c1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v1-c1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v1-c1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v1-c1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v1-c1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v1-c1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v1-c1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v1-c1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.43s
cycy233-l3-e-v1-c1_v1 status is now torndown due to DeploymentManager action