submission_id: cycy233-l3-ba-e-v7-c2_v1
developer_uid: shiroe40
alignment_samples: 0
best_of: 16
celo_rating: 1257.52
display_name: auto
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': 1.0, '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, 'reward_max_token_input': 256}
is_internal_developer: False
language_model: cycy233/L3-ba-e-v7-c2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-ba-e-v7-c2
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-ba-e-v7-c2
model_size: 8B
num_battles: 10901
num_wins: 6128
propriety_score: 0.7145748987854251
propriety_total_count: 988.0
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: Jellywibble/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-28T02:11:05+00:00
us_pacific_date: 2024-07-27
win_ratio: 0.5621502614439042
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-ba-e-v7-c2-v1-mkmlizer
Waiting for job on cycy233-l3-ba-e-v7-c2-v1-mkmlizer to finish
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ /___/ ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ Version: 0.9.7 ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ║ ║
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: Downloaded to shared memory in 36.508s
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphv2kr4ya, device:0
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: quantized model in 26.600s
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: Processed model cycy233/L3-ba-e-v7-c2 in 63.108s
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-ba-e-v7-c2-v1
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v7-c2-v1/config.json
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v7-c2-v1/special_tokens_map.json
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v7-c2-v1/tokenizer_config.json
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v7-c2-v1/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ba-e-v7-c2-v1/flywheel_model.0.safetensors
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:07, 36.04it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:05, 46.65it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:04, 57.65it/s] Loading 0: 10%|▉ | 29/291 [00:00<00:04, 54.44it/s] Loading 0: 12%|█▏ | 35/291 [00:00<00:04, 53.98it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:05, 46.43it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:04, 54.06it/s] Loading 0: 19%|█▉ | 55/291 [00:01<00:04, 49.63it/s] Loading 0: 21%|██ | 61/291 [00:01<00:04, 50.33it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 51.71it/s] Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 47.71it/s] Loading 0: 27%|██▋ | 78/291 [00:01<00:04, 46.24it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:06, 34.08it/s] Loading 0: 30%|██▉ | 87/291 [00:01<00:05, 34.37it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:04, 41.22it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 40.10it/s] Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 41.05it/s] Loading 0: 38%|███▊ | 111/291 [00:02<00:03, 45.37it/s] Loading 0: 40%|███▉ | 116/291 [00:02<00:03, 45.11it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 45.09it/s] Loading 0: 44%|████▎ | 127/291 [00:02<00:03, 41.85it/s] Loading 0: 45%|████▌ | 132/291 [00:02<00:03, 41.22it/s] Loading 0: 47%|████▋ | 138/291 [00:03<00:03, 45.53it/s] Loading 0: 49%|████▉ | 143/291 [00:03<00:03, 45.21it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:03, 45.43it/s] Loading 0: 53%|█████▎ | 153/291 [00:03<00:02, 46.60it/s] Loading 0: 54%|█████▍ | 158/291 [00:03<00:03, 37.52it/s] Loading 0: 57%|█████▋ | 165/291 [00:03<00:02, 45.07it/s] Loading 0: 58%|█████▊ | 170/291 [00:03<00:02, 45.10it/s] Loading 0: 60%|██████ | 176/291 [00:03<00:02, 48.47it/s] Loading 0: 63%|██████▎ | 182/291 [00:04<00:02, 41.76it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:03, 31.18it/s] Loading 0: 66%|██████▌ | 191/291 [00:04<00:03, 32.89it/s] Loading 0: 67%|██████▋ | 195/291 [00:04<00:02, 32.76it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 39.73it/s] Loading 0: 71%|███████▏ | 208/291 [00:04<00:02, 38.60it/s] Loading 0: 73%|███████▎ | 213/291 [00:04<00:01, 39.25it/s] Loading 0: 76%|███████▌ | 220/291 [00:05<00:01, 44.93it/s] Loading 0: 78%|███████▊ | 226/291 [00:05<00:01, 42.83it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 43.00it/s] Loading 0: 81%|████████▏ | 237/291 [00:05<00:01, 46.88it/s] Loading 0: 83%|████████▎ | 242/291 [00:05<00:01, 47.34it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 47.73it/s] Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 42.97it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 42.25it/s] Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 47.37it/s] Loading 0: 93%|█████████▎| 271/291 [00:06<00:00, 40.84it/s] Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 41.01it/s] Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 39.65it/s] Loading 0: 99%|█████████▊| 287/291 [00:11<00:01, 3.20it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ba-e-v7-c2-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-ba-e-v7-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: Saving duration: 1.353s
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.549s
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ba-e-v7-c2-v1_reward
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ba-e-v7-c2-v1_reward/special_tokens_map.json
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ba-e-v7-c2-v1_reward/config.json
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ba-e-v7-c2-v1_reward/tokenizer_config.json
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ba-e-v7-c2-v1_reward/merges.txt
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ba-e-v7-c2-v1_reward/vocab.json
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-ba-e-v7-c2-v1_reward/tokenizer.json
cycy233-l3-ba-e-v7-c2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ba-e-v7-c2-v1_reward/reward.tensors
Job cycy233-l3-ba-e-v7-c2-v1-mkmlizer completed after 104.74s with status: succeeded
Stopping job with name cycy233-l3-ba-e-v7-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.98s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ba-e-v7-c2-v1
Waiting for inference service cycy233-l3-ba-e-v7-c2-v1 to be ready
Inference service cycy233-l3-ba-e-v7-c2-v1 ready after 90.66745662689209s
Pipeline stage ISVCDeployer completed in 92.01s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.231799840927124s
Received healthy response to inference request in 1.4733569622039795s
Received healthy response to inference request in 1.42161226272583s
Received healthy response to inference request in 1.3738453388214111s
Received healthy response to inference request in 1.4633305072784424s
5 requests
0 failed requests
5th percentile: 1.3833987236022949
10th percentile: 1.3929521083831786
20th percentile: 1.4120588779449463
30th percentile: 1.4299559116363525
40th percentile: 1.4466432094573975
50th percentile: 1.4633305072784424
60th percentile: 1.4673410892486571
70th percentile: 1.4713516712188721
80th percentile: 1.6250455379486086
90th percentile: 1.9284226894378662
95th percentile: 2.080111265182495
99th percentile: 2.2014621257781983
mean time: 1.5927889823913575
Pipeline stage StressChecker completed in 8.67s
cycy233-l3-ba-e-v7-c2_v1 status is now deployed due to DeploymentManager action
cycy233-l3-ba-e-v7-c2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-ba-e-v7-c2_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-ba-e-v7-c2-v1 is running
Tearing down inference service cycy233-l3-ba-e-v7-c2-v1
Service cycy233-l3-ba-e-v7-c2-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.41s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-ba-e-v7-c2-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v7-c2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v7-c2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v7-c2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v7-c2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-ba-e-v7-c2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v7-c2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v7-c2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v7-c2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v7-c2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v7-c2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v7-c2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.65s
cycy233-l3-ba-e-v7-c2_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics