developer_uid: shiroe40
submission_id: cycy233-l3-e-v2-c1_v11
model_name: auto
model_group: cycy233/L3-e-v2-c1
status: torndown
timestamp: 2024-07-23T02:13:33+00:00
num_battles: 14434
num_wins: 8421
celo_rating: 1261.3
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-e-v2-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-v2-c1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-22
win_ratio: 0.5834141610087293
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, '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-v2-c1-v11-mkmlizer
Waiting for job on cycy233-l3-e-v2-c1-v11-mkmlizer to finish
cycy233-l3-e-v2-c1-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ _____ __ __ ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ /___/ ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ Version: 0.9.5.post3 ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ belonging to: ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c1-v11-mkmlizer: Downloaded to shared memory in 25.022s
cycy233-l3-e-v2-c1-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp23gcuhta, device:0
cycy233-l3-e-v2-c1-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mistral-nemo-i_9330_v9: ('http://mistralai-mistral-nemo-i-9330-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
cycy233-l3-e-v2-c1-v11-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 37.46it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:02, 101.54it/s] Loading 0: 11%|█ | 32/291 [00:00<00:02, 105.41it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:02, 117.68it/s] Loading 0: 21%|██ | 60/291 [00:00<00:01, 116.67it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:01, 123.87it/s] Loading 0: 31%|███ | 89/291 [00:00<00:02, 75.93it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 86.93it/s] Loading 0: 41%|████ | 118/291 [00:01<00:01, 100.72it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 104.19it/s] Loading 0: 49%|████▉ | 144/291 [00:01<00:01, 112.82it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 115.51it/s] Loading 0: 59%|█████▉ | 172/291 [00:01<00:00, 124.62it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 83.72it/s] Loading 0: 68%|██████▊ | 198/291 [00:02<00:01, 88.52it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:00, 97.15it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 110.40it/s] Loading 0: 83%|████████▎ | 241/291 [00:02<00:00, 114.06it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 119.84it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 126.27it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 8.40it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-e-v2-c1-v11-mkmlizer: quantized model in 22.998s
cycy233-l3-e-v2-c1-v11-mkmlizer: Processed model cycy233/L3-e-v2-c1 in 48.020s
cycy233-l3-e-v2-c1-v11-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c1-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c1-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v11
cycy233-l3-e-v2-c1-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v11/config.json
cycy233-l3-e-v2-c1-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v11/special_tokens_map.json
cycy233-l3-e-v2-c1-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v11/tokenizer_config.json
cycy233-l3-e-v2-c1-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v11/tokenizer.json
cycy233-l3-e-v2-c1-v11-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v2-c1-v11-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-c1-v11-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c1-v11-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-c1-v11-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c1-v11-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-c1-v11-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c1-v11-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c1-v11-mkmlizer: Saving duration: 1.377s
cycy233-l3-e-v2-c1-v11-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.268s
cycy233-l3-e-v2-c1-v11-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c1-v11-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v2-c1-v11-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v11_reward
cycy233-l3-e-v2-c1-v11-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v11_reward/config.json
cycy233-l3-e-v2-c1-v11-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v11_reward/tokenizer_config.json
cycy233-l3-e-v2-c1-v11-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v11_reward/special_tokens_map.json
cycy233-l3-e-v2-c1-v11-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v11_reward/merges.txt
cycy233-l3-e-v2-c1-v11-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v11_reward/vocab.json
cycy233-l3-e-v2-c1-v11-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v11_reward/tokenizer.json
cycy233-l3-e-v2-c1-v11-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v11_reward/reward.tensors
Job cycy233-l3-e-v2-c1-v11-mkmlizer completed after 94.38s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c1-v11-mkmlizer
Pipeline stage MKMLizer completed in 95.44s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c1-v11
Waiting for inference service cycy233-l3-e-v2-c1-v11 to be ready
Failed to get response for submission mistralai-mistral-nemo-i_9330_v9: ('http://mistralai-mistral-nemo-i-9330-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
Inference service cycy233-l3-e-v2-c1-v11 ready after 50.93173336982727s
Pipeline stage ISVCDeployer completed in 52.73s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.380239963531494s
Received healthy response to inference request in 1.4833893775939941s
Received healthy response to inference request in 1.468817949295044s
Received healthy response to inference request in 1.4327683448791504s
Received healthy response to inference request in 1.5082988739013672s
5 requests
0 failed requests
5th percentile: 1.439978265762329
10th percentile: 1.4471881866455079
20th percentile: 1.4616080284118653
30th percentile: 1.471732234954834
40th percentile: 1.477560806274414
50th percentile: 1.4833893775939941
60th percentile: 1.4933531761169434
70th percentile: 1.5033169746398927
80th percentile: 1.6826870918273928
90th percentile: 2.0314635276794433
95th percentile: 2.2058517456054685
99th percentile: 2.345362319946289
mean time: 1.65470290184021
Pipeline stage StressChecker completed in 8.90s
cycy233-l3-e-v2-c1_v11 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c1_v11 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c1_v11
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c1-v11 is running
Tearing down inference service cycy233-l3-e-v2-c1-v11
Service cycy233-l3-e-v2-c1-v11 has been torndown
Pipeline stage ISVCDeleter completed in 4.63s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v11/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v11/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v11/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v11/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v11/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v11_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v11_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v11_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v11_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v11_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v11_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v11_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.30s
cycy233-l3-e-v2-c1_v11 status is now torndown due to DeploymentManager action