developer_uid: shiroe40
submission_id: cycy233-l3-e-v2-c1_v3
model_name: auto
model_group: cycy233/L3-e-v2-c1
status: torndown
timestamp: 2024-07-20T01:45:13+00:00
num_battles: 6635
num_wins: 3707
celo_rating: 1257.64
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: 8
max_input_tokens: 1024
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: 2024-07-19
win_ratio: 0.5587038432554634
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': 1024, 'best_of': 8, '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-v3-mkmlizer
Waiting for job on cycy233-l3-e-v2-c1-v3-mkmlizer to finish
cycy233-l3-e-v2-c1-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ _____ __ __ ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ /___/ ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ Version: 0.9.5.post3 ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ belonging to: ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ║ ║
cycy233-l3-e-v2-c1-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c1-v3-mkmlizer: Downloaded to shared memory in 20.687s
cycy233-l3-e-v2-c1-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2t_gfl84, device:0
cycy233-l3-e-v2-c1-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v2-c1-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 121.30it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 141.36it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 139.99it/s] Loading 0: 20%|██ | 59/291 [00:00<00:01, 132.77it/s] Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 141.58it/s] Loading 0: 31%|███ | 90/291 [00:00<00:02, 84.80it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:02, 93.76it/s] Loading 0: 41%|████ | 118/291 [00:01<00:01, 106.85it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 107.18it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 118.67it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:00, 126.79it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 127.18it/s] Loading 0: 67%|██████▋ | 194/291 [00:01<00:01, 85.32it/s] Loading 0: 73%|███████▎ | 211/291 [00:01<00:00, 99.50it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 111.11it/s] Loading 0: 83%|████████▎ | 241/291 [00:02<00:00, 115.04it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 120.75it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 128.49it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 8.83it/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-v3-mkmlizer: quantized model in 22.241s
cycy233-l3-e-v2-c1-v3-mkmlizer: Processed model cycy233/L3-e-v2-c1 in 42.929s
cycy233-l3-e-v2-c1-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c1-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c1-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v3
cycy233-l3-e-v2-c1-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v3/config.json
cycy233-l3-e-v2-c1-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v3/special_tokens_map.json
cycy233-l3-e-v2-c1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v3/tokenizer_config.json
cycy233-l3-e-v2-c1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v3/tokenizer.json
cycy233-l3-e-v2-c1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v3/flywheel_model.0.safetensors
cycy233-l3-e-v2-c1-v3-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v2-c1-v3-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-v3-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c1-v3-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-v3-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c1-v3-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-v3-mkmlizer: warnings.warn(
cycy233-l3-e-v2-c1-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c1-v3-mkmlizer: Saving duration: 1.460s
cycy233-l3-e-v2-c1-v3-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.726s
cycy233-l3-e-v2-c1-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c1-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v2-c1-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v3_reward
cycy233-l3-e-v2-c1-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v3_reward/config.json
cycy233-l3-e-v2-c1-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v3_reward/special_tokens_map.json
cycy233-l3-e-v2-c1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v3_reward/tokenizer_config.json
cycy233-l3-e-v2-c1-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v3_reward/merges.txt
cycy233-l3-e-v2-c1-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v3_reward/vocab.json
cycy233-l3-e-v2-c1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v3_reward/tokenizer.json
cycy233-l3-e-v2-c1-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v3_reward/reward.tensors
Job cycy233-l3-e-v2-c1-v3-mkmlizer completed after 88.0s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c1-v3-mkmlizer
Pipeline stage MKMLizer completed in 89.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c1-v3
Waiting for inference service cycy233-l3-e-v2-c1-v3 to be ready
Failed to get response for submission pawankrd-cosmosrp_v73: ('http://pawankrd-cosmosrp-v73-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission pawankrd-cosmosrp_v73: ('http://pawankrd-cosmosrp-v73-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission pawankrd-cosmosrp_v73: ('http://pawankrd-cosmosrp-v73-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission pawankrd-cosmosrp_v73: ('http://pawankrd-cosmosrp-v73-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service cycy233-l3-e-v2-c1-v3 ready after 50.915703535079956s
Pipeline stage ISVCDeployer completed in 53.47s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1237518787384033s
Received healthy response to inference request in 1.1997218132019043s
Received healthy response to inference request in 1.285125970840454s
Received healthy response to inference request in 1.2974121570587158s
Received healthy response to inference request in 1.2586326599121094s
5 requests
0 failed requests
5th percentile: 1.2115039825439453
10th percentile: 1.2232861518859863
20th percentile: 1.2468504905700684
30th percentile: 1.2639313220977784
40th percentile: 1.2745286464691161
50th percentile: 1.285125970840454
60th percentile: 1.2900404453277587
70th percentile: 1.2949549198150634
80th percentile: 1.4626801013946535
90th percentile: 1.7932159900665283
95th percentile: 1.9584839344024656
99th percentile: 2.0906982898712156
mean time: 1.4329288959503175
Pipeline stage StressChecker completed in 7.79s
cycy233-l3-e-v2-c1_v3 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c1_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c1_v3
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c1-v3 is running
Tearing down inference service cycy233-l3-e-v2-c1-v3
Service cycy233-l3-e-v2-c1-v3 has been torndown
Pipeline stage ISVCDeleter completed in 4.43s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v3/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v3_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.40s
cycy233-l3-e-v2-c1_v3 status is now torndown due to DeploymentManager action