developer_uid: shiroe40
submission_id: cycy233-l3-be-a-v0-c4_v1
model_name: auto
model_group: cycy233/L3-be-a-v0-c4
status: torndown
timestamp: 2024-07-19T06:14:27+00:00
num_battles: 6598
num_wins: 2841
celo_rating: 1150.51
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-be-a-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-a-v0-c4
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-18
win_ratio: 0.43058502576538343
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-a-v0-c4-v1-mkmlizer
Waiting for job on cycy233-l3-be-a-v0-c4-v1-mkmlizer to finish
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ /___/ ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ Version: 0.9.5.post3 ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-be-a-v0-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-be-a-v0-c4-v1-mkmlizer: Downloaded to shared memory in 32.428s
cycy233-l3-be-a-v0-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpemua25qj, device:0
cycy233-l3-be-a-v0-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-be-a-v0-c4-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 100.75it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:02, 92.98it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 114.51it/s] Loading 0: 18%|█▊ | 51/291 [00:00<00:02, 110.40it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 120.60it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:01, 115.87it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:03, 50.15it/s] Loading 0: 34%|███▍ | 100/291 [00:01<00:03, 53.88it/s] Loading 0: 38%|███▊ | 111/291 [00:01<00:02, 62.39it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:02, 70.11it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 87.88it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 88.64it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 103.76it/s] Loading 0: 62%|██████▏ | 179/291 [00:02<00:01, 111.25it/s] Loading 0: 66%|██████▌ | 192/291 [00:02<00:01, 55.78it/s] Loading 0: 70%|██████▉ | 203/291 [00:02<00:01, 63.14it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 79.19it/s] Loading 0: 79%|███████▉ | 231/291 [00:02<00:00, 84.92it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 98.04it/s] Loading 0: 89%|████████▊ | 258/291 [00:03<00:00, 100.98it/s] Loading 0: 94%|█████████▍| 273/291 [00:03<00:00, 111.94it/s] Loading 0: 98%|█████████▊| 286/291 [00:03<00:00, 114.80it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-be-a-v0-c4-v1-mkmlizer: quantized model in 29.219s
cycy233-l3-be-a-v0-c4-v1-mkmlizer: Processed model cycy233/L3-be-a-v0-c4 in 61.648s
cycy233-l3-be-a-v0-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-be-a-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-be-a-v0-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-be-a-v0-c4-v1
cycy233-l3-be-a-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-be-a-v0-c4-v1/tokenizer_config.json
cycy233-l3-be-a-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-be-a-v0-c4-v1/special_tokens_map.json
cycy233-l3-be-a-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-be-a-v0-c4-v1/config.json
cycy233-l3-be-a-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-be-a-v0-c4-v1/tokenizer.json
cycy233-l3-be-a-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-be-a-v0-c4-v1/flywheel_model.0.safetensors
cycy233-l3-be-a-v0-c4-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-be-a-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-a-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-be-a-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-a-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-be-a-v0-c4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-be-a-v0-c4-v1-mkmlizer: Saving duration: 2.282s
cycy233-l3-be-a-v0-c4-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 14.718s
cycy233-l3-be-a-v0-c4-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-be-a-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-be-a-v0-c4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-be-a-v0-c4-v1_reward
cycy233-l3-be-a-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-be-a-v0-c4-v1_reward/config.json
cycy233-l3-be-a-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-be-a-v0-c4-v1_reward/special_tokens_map.json
cycy233-l3-be-a-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-be-a-v0-c4-v1_reward/tokenizer_config.json
cycy233-l3-be-a-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-be-a-v0-c4-v1_reward/merges.txt
cycy233-l3-be-a-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-be-a-v0-c4-v1_reward/vocab.json
cycy233-l3-be-a-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-be-a-v0-c4-v1_reward/tokenizer.json
cycy233-l3-be-a-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-be-a-v0-c4-v1_reward/reward.tensors
Job cycy233-l3-be-a-v0-c4-v1-mkmlizer completed after 116.94s with status: succeeded
Stopping job with name cycy233-l3-be-a-v0-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 118.11s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-be-a-v0-c4-v1
Waiting for inference service cycy233-l3-be-a-v0-c4-v1 to be ready
Inference service cycy233-l3-be-a-v0-c4-v1 ready after 163.2834656238556s
Pipeline stage ISVCDeployer completed in 165.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.205413341522217s
Received healthy response to inference request in 1.5031464099884033s
Received healthy response to inference request in 1.4587907791137695s
Received healthy response to inference request in 1.4444777965545654s
Received healthy response to inference request in 1.5018384456634521s
5 requests
0 failed requests
5th percentile: 1.4473403930664062
10th percentile: 1.4502029895782471
20th percentile: 1.4559281826019288
30th percentile: 1.467400312423706
40th percentile: 1.484619379043579
50th percentile: 1.5018384456634521
60th percentile: 1.5023616313934327
70th percentile: 1.502884817123413
80th percentile: 1.643599796295166
90th percentile: 1.9245065689086915
95th percentile: 2.064959955215454
99th percentile: 2.1773226642608643
mean time: 1.6227333545684814
Pipeline stage StressChecker completed in 8.78s
cycy233-l3-be-a-v0-c4_v1 status is now deployed due to DeploymentManager action
cycy233-l3-be-a-v0-c4_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-be-a-v0-c4_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-be-a-v0-c4-v1 is running
Tearing down inference service cycy233-l3-be-a-v0-c4-v1
Service cycy233-l3-be-a-v0-c4-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.71s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-be-a-v0-c4-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-be-a-v0-c4-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-be-a-v0-c4-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-be-a-v0-c4-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-be-a-v0-c4-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-be-a-v0-c4-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-be-a-v0-c4-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-be-a-v0-c4-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-be-a-v0-c4-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-be-a-v0-c4-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-be-a-v0-c4-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-be-a-v0-c4-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.80s
cycy233-l3-be-a-v0-c4_v1 status is now torndown due to DeploymentManager action