submission_id: cycy233-l3-ba-v0-c3_v1
developer_uid: shiroe40
alignment_samples: 0
best_of: 16
celo_rating: 1237.18
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}
is_internal_developer: False
language_model: cycy233/L3-ba-v0-c3
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-ba-v0-c3
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-ba-v0-c3
model_size: 8B
num_battles: 6528
num_wins: 3591
propriety_score: 0.7263701350277998
propriety_total_count: 2518.0
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: 2024-07-19T03:00:36+00:00
us_pacific_date: 2024-07-18
win_ratio: 0.5500919117647058
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-ba-v0-c3-v1-mkmlizer
Waiting for job on cycy233-l3-ba-v0-c3-v1-mkmlizer to finish
cycy233-l3-ba-v0-c3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ /___/ ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ Version: 0.9.5.post3 ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-ba-v0-c3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ba-v0-c3-v1-mkmlizer: Downloaded to shared memory in 36.178s
cycy233-l3-ba-v0-c3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp477f_af1, device:0
cycy233-l3-ba-v0-c3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ba-v0-c3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 57.09it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 67.62it/s] Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 96.76it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-ba-v0-c3-v1-mkmlizer: quantized model in 30.592s
cycy233-l3-ba-v0-c3-v1-mkmlizer: Processed model cycy233/L3-ba-v0-c3 in 66.770s
cycy233-l3-ba-v0-c3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ba-v0-c3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-ba-v0-c3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-ba-v0-c3-v1
cycy233-l3-ba-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-ba-v0-c3-v1/config.json
cycy233-l3-ba-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-ba-v0-c3-v1/special_tokens_map.json
cycy233-l3-ba-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-ba-v0-c3-v1/tokenizer_config.json
cycy233-l3-ba-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-ba-v0-c3-v1/tokenizer.json
cycy233-l3-ba-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ba-v0-c3-v1/flywheel_model.0.safetensors
cycy233-l3-ba-v0-c3-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-ba-v0-c3-v1-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-ba-v0-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-ba-v0-c3-v1-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-ba-v0-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-ba-v0-c3-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-v0-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-ba-v0-c3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ba-v0-c3-v1-mkmlizer: Saving duration: 2.365s
cycy233-l3-ba-v0-c3-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 15.918s
cycy233-l3-ba-v0-c3-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ba-v0-c3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ba-v0-c3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ba-v0-c3-v1_reward
cycy233-l3-ba-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ba-v0-c3-v1_reward/reward.tensors
Job cycy233-l3-ba-v0-c3-v1-mkmlizer completed after 111.64s with status: succeeded
Stopping job with name cycy233-l3-ba-v0-c3-v1-mkmlizer
Pipeline stage MKMLizer completed in 113.44s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ba-v0-c3-v1
Waiting for inference service cycy233-l3-ba-v0-c3-v1 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')
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
Inference service cycy233-l3-ba-v0-c3-v1 ready after 72.04552698135376s
Pipeline stage ISVCDeployer completed in 74.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.325392484664917s
Received healthy response to inference request in 1.4774200916290283s
Received healthy response to inference request in 1.4441611766815186s
Received healthy response to inference request in 1.4265468120574951s
Received healthy response to inference request in 1.4799268245697021s
5 requests
0 failed requests
5th percentile: 1.4300696849822998
10th percentile: 1.4335925579071045
20th percentile: 1.4406383037567139
30th percentile: 1.4508129596710204
40th percentile: 1.4641165256500244
50th percentile: 1.4774200916290283
60th percentile: 1.4784227848052978
70th percentile: 1.4794254779815674
80th percentile: 1.6490199565887453
90th percentile: 1.987206220626831
95th percentile: 2.156299352645874
99th percentile: 2.2915738582611085
mean time: 1.6306894779205323
Pipeline stage StressChecker completed in 8.85s
cycy233-l3-ba-v0-c3_v1 status is now deployed due to DeploymentManager action
cycy233-l3-ba-v0-c3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-ba-v0-c3_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-ba-v0-c3-v1 is running
Tearing down inference service cycy233-l3-ba-v0-c3-v1
Service cycy233-l3-ba-v0-c3-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.49s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-ba-v0-c3-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-v0-c3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-v0-c3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-v0-c3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-v0-c3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-ba-v0-c3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v0-c3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v0-c3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v0-c3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v0-c3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v0-c3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v0-c3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.28s
cycy233-l3-ba-v0-c3_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics