developer_uid: shiroe40
submission_id: cycy233-l3-ba-v3-c2_v1
model_name: auto
model_group: cycy233/L3-ba-v3-c2
status: torndown
timestamp: 2024-08-05T01:45:21+00:00
num_battles: 9208
num_wins: 5007
celo_rating: 1228.89
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-ba-v3-c2
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-ba-v3-c2
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-04
win_ratio: 0.54376629018245
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}
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-ba-v3-c2-v1-mkmlizer
Waiting for job on cycy233-l3-ba-v3-c2-v1-mkmlizer to finish
cycy233-l3-ba-v3-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ /___/ ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ Version: 0.9.9 ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ║ ║
cycy233-l3-ba-v3-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ba-v3-c2-v1-mkmlizer: Downloaded to shared memory in 43.852s
cycy233-l3-ba-v3-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpno36um9f, device:0
cycy233-l3-ba-v3-c2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ba-v3-c2-v1-mkmlizer: quantized model in 25.195s
cycy233-l3-ba-v3-c2-v1-mkmlizer: Processed model cycy233/L3-ba-v3-c2 in 69.046s
cycy233-l3-ba-v3-c2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ba-v3-c2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-ba-v3-c2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-ba-v3-c2-v1
cycy233-l3-ba-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-ba-v3-c2-v1/config.json
cycy233-l3-ba-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-ba-v3-c2-v1/special_tokens_map.json
cycy233-l3-ba-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-ba-v3-c2-v1/tokenizer_config.json
cycy233-l3-ba-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-ba-v3-c2-v1/tokenizer.json
cycy233-l3-ba-v3-c2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ba-v3-c2-v1/flywheel_model.0.safetensors
cycy233-l3-ba-v3-c2-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-ba-v3-c2-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 39.28it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:04, 68.35it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 76.42it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 80.48it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 91.18it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 90.33it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 89.48it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 81.82it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:09, 21.93it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 28.20it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 35.27it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 43.05it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 50.76it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:02, 58.47it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 62.50it/s] Loading 0: 54%|█████▍ | 157/291 [00:02<00:01, 74.36it/s] Loading 0: 58%|█████▊ | 169/291 [00:03<00:01, 76.85it/s] Loading 0: 61%|██████ | 178/291 [00:03<00:01, 79.29it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 24.04it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 34.20it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:01, 41.79it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 52.89it/s] Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 59.66it/s] Loading 0: 88%|████████▊ | 256/291 [00:04<00:00, 70.10it/s] Loading 0: 91%|█████████▏| 266/291 [00:05<00:00, 75.13it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 74.65it/s] Loading 0: 99%|█████████▊| 287/291 [00:05<00:00, 46.95it/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-v3-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ba-v3-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-v3-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ba-v3-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-v3-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ba-v3-c2-v1-mkmlizer: Saving duration: 1.396s
cycy233-l3-ba-v3-c2-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.648s
cycy233-l3-ba-v3-c2-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ba-v3-c2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ba-v3-c2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ba-v3-c2-v1_reward
cycy233-l3-ba-v3-c2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ba-v3-c2-v1_reward/special_tokens_map.json
cycy233-l3-ba-v3-c2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ba-v3-c2-v1_reward/tokenizer_config.json
cycy233-l3-ba-v3-c2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ba-v3-c2-v1_reward/config.json
cycy233-l3-ba-v3-c2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ba-v3-c2-v1_reward/merges.txt
cycy233-l3-ba-v3-c2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ba-v3-c2-v1_reward/vocab.json
cycy233-l3-ba-v3-c2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-ba-v3-c2-v1_reward/tokenizer.json
cycy233-l3-ba-v3-c2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ba-v3-c2-v1_reward/reward.tensors
Job cycy233-l3-ba-v3-c2-v1-mkmlizer completed after 115.0s with status: succeeded
Stopping job with name cycy233-l3-ba-v3-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ba-v3-c2-v1
Waiting for inference service cycy233-l3-ba-v3-c2-v1 to be ready
Inference service cycy233-l3-ba-v3-c2-v1 ready after 161.17832708358765s
Pipeline stage ISVCDeployer completed in 163.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1574459075927734s
Received healthy response to inference request in 1.4226629734039307s
Received healthy response to inference request in 1.4016499519348145s
Received healthy response to inference request in 1.4353837966918945s
Received healthy response to inference request in 1.4473035335540771s
5 requests
0 failed requests
5th percentile: 1.4058525562286377
10th percentile: 1.410055160522461
20th percentile: 1.4184603691101074
30th percentile: 1.4252071380615234
40th percentile: 1.430295467376709
50th percentile: 1.4353837966918945
60th percentile: 1.4401516914367676
70th percentile: 1.4449195861816406
80th percentile: 1.5893320083618165
90th percentile: 1.873388957977295
95th percentile: 2.015417432785034
99th percentile: 2.1290402126312253
mean time: 1.572889232635498
Pipeline stage StressChecker completed in 8.62s
cycy233-l3-ba-v3-c2_v1 status is now deployed due to DeploymentManager action
cycy233-l3-ba-v3-c2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-ba-v3-c2_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-ba-v3-c2-v1 is running
Tearing down inference service cycy233-l3-ba-v3-c2-v1
Service cycy233-l3-ba-v3-c2-v1 has been torndown
Pipeline stage ISVCDeleter completed in 5.67s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-ba-v3-c2-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-v3-c2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-v3-c2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-v3-c2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-v3-c2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-ba-v3-c2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v3-c2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v3-c2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v3-c2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v3-c2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v3-c2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v3-c2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.47s
cycy233-l3-ba-v3-c2_v1 status is now torndown due to DeploymentManager action