developer_uid: shiroe40
submission_id: cycy233-l3-e-v2-c4_v4
model_name: auto
model_group: cycy233/L3-e-v2-c4
status: torndown
timestamp: 2024-07-20T03:53:13+00:00
num_battles: 8649
num_wins: 4990
celo_rating: 1267.45
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-e-v2-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-e-v2-c4
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-19
win_ratio: 0.5769453115967164
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], '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-v2-c4-v4-mkmlizer
Waiting for job on cycy233-l3-e-v2-c4-v4-mkmlizer to finish
cycy233-l3-e-v2-c4-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ _____ __ __ ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ /___/ ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ Version: 0.9.5.post3 ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ belonging to: ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ║ ║
cycy233-l3-e-v2-c4-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c4-v4-mkmlizer: Downloaded to shared memory in 23.596s
cycy233-l3-e-v2-c4-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpm3p15wxg, device:0
cycy233-l3-e-v2-c4-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v2-c4-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 111.75it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:02, 120.47it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 122.43it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 116.47it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 119.07it/s] Loading 0: 27%|██▋ | 78/291 [00:00<00:01, 114.14it/s] Loading 0: 31%|███ | 90/291 [00:00<00:02, 72.55it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 83.12it/s] Loading 0: 40%|███▉ | 115/291 [00:01<00:01, 91.23it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 98.87it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 97.50it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 111.08it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 110.66it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:00, 111.95it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 74.07it/s] Loading 0: 71%|███████ | 207/291 [00:02<00:00, 87.00it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 94.71it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 107.91it/s] Loading 0: 86%|████████▌ | 250/291 [00:02<00:00, 110.97it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 116.12it/s] Loading 0: 95%|█████████▌| 277/291 [00:02<00:00, 114.93it/s] Loading 0: 99%|█████████▉| 289/291 [00:08<00:00, 7.43it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-e-v2-c4-v4-mkmlizer: quantized model in 23.084s
cycy233-l3-e-v2-c4-v4-mkmlizer: Processed model cycy233/L3-e-v2-c4 in 46.681s
cycy233-l3-e-v2-c4-v4-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c4-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c4-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v4
cycy233-l3-e-v2-c4-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v4/config.json
cycy233-l3-e-v2-c4-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v4/tokenizer_config.json
cycy233-l3-e-v2-c4-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v4/special_tokens_map.json
cycy233-l3-e-v2-c4-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v4/tokenizer.json
cycy233-l3-e-v2-c4-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v4/flywheel_model.0.safetensors
cycy233-l3-e-v2-c4-v4-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v2-c4-v4-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-v2-c4-v4-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c4-v4-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-v2-c4-v4-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c4-v4-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-v2-c4-v4-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c4-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c4-v4-mkmlizer: Saving duration: 1.364s
cycy233-l3-e-v2-c4-v4-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.670s
cycy233-l3-e-v2-c4-v4-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c4-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v2-c4-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v4_reward
cycy233-l3-e-v2-c4-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v4_reward/tokenizer_config.json
cycy233-l3-e-v2-c4-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v4_reward/config.json
cycy233-l3-e-v2-c4-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v4_reward/special_tokens_map.json
cycy233-l3-e-v2-c4-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v4_reward/merges.txt
cycy233-l3-e-v2-c4-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v4_reward/vocab.json
cycy233-l3-e-v2-c4-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v4_reward/tokenizer.json
cycy233-l3-e-v2-c4-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v4_reward/reward.tensors
Job cycy233-l3-e-v2-c4-v4-mkmlizer completed after 90.35s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c4-v4-mkmlizer
Pipeline stage MKMLizer completed in 91.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c4-v4
Waiting for inference service cycy233-l3-e-v2-c4-v4 to be ready
Inference service cycy233-l3-e-v2-c4-v4 ready after 40.89277672767639s
Pipeline stage ISVCDeployer completed in 42.64s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2569468021392822s
Received healthy response to inference request in 1.4573643207550049s
Received healthy response to inference request in 1.4483802318572998s
Received healthy response to inference request in 1.4322361946105957s
Received healthy response to inference request in 1.4860584735870361s
5 requests
0 failed requests
5th percentile: 1.4354650020599364
10th percentile: 1.4386938095092774
20th percentile: 1.445151424407959
30th percentile: 1.450177049636841
40th percentile: 1.453770685195923
50th percentile: 1.4573643207550049
60th percentile: 1.4688419818878173
70th percentile: 1.4803196430206298
80th percentile: 1.6402361392974856
90th percentile: 1.9485914707183838
95th percentile: 2.102769136428833
99th percentile: 2.2261112689971925
mean time: 1.6161972045898438
Pipeline stage StressChecker completed in 8.68s
cycy233-l3-e-v2-c4_v4 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c4_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c4_v4
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c4-v4 is running
Tearing down inference service cycy233-l3-e-v2-c4-v4
Service cycy233-l3-e-v2-c4-v4 has been torndown
Pipeline stage ISVCDeleter completed in 5.14s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c4-v4/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c4-v4_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.27s
cycy233-l3-e-v2-c4_v4 status is now torndown due to DeploymentManager action