developer_uid: shiroe40
submission_id: cycy233-l3-ea-v0-c2_v1
model_name: auto
model_group: cycy233/L3-ea-v0-c2
status: torndown
timestamp: 2024-07-16T05:43:34+00:00
num_battles: 146770
num_wins: 66839
celo_rating: 1180.8
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-ea-v0-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-ea-v0-c2
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-15
win_ratio: 0.4553996048238741
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}
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-ea-v0-c2-v1-mkmlizer
Waiting for job on cycy233-l3-ea-v0-c2-v1-mkmlizer to finish
cycy233-l3-ea-v0-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ /___/ ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ Version: 0.9.5.post2 ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ║ ║
cycy233-l3-ea-v0-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
cycy233-l3-ea-v0-c2-v1-mkmlizer: Downloaded to shared memory in 39.400s
cycy233-l3-ea-v0-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-ea-v0-c2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ea-v0-c2-v1-mkmlizer: lm_head.weight torch.Size([139542528])
cycy233-l3-ea-v0-c2-v1-mkmlizer: model.layers.31.input_layernorm.weight torch.Size([4096])
cycy233-l3-ea-v0-c2-v1-mkmlizer: model.layers.31.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-ea-v0-c2-v1-mkmlizer: model.layers.31.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-ea-v0-c2-v1-mkmlizer: model.norm.weight torch.Size([4096])
cycy233-l3-ea-v0-c2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ea-v0-c2-v1/flywheel_model.0.safetensors
cycy233-l3-ea-v0-c2-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-ea-v0-c2-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-ea-v0-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ea-v0-c2-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-ea-v0-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ea-v0-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-ea-v0-c2-v1-mkmlizer: warnings.warn(
cycy233-l3-ea-v0-c2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ea-v0-c2-v1-mkmlizer: Saving duration: 2.405s
cycy233-l3-ea-v0-c2-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 17.312s
cycy233-l3-ea-v0-c2-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ea-v0-c2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ea-v0-c2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ea-v0-c2-v1_reward
cycy233-l3-ea-v0-c2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ea-v0-c2-v1_reward/config.json
cycy233-l3-ea-v0-c2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ea-v0-c2-v1_reward/tokenizer_config.json
cycy233-l3-ea-v0-c2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ea-v0-c2-v1_reward/special_tokens_map.json
cycy233-l3-ea-v0-c2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ea-v0-c2-v1_reward/merges.txt
cycy233-l3-ea-v0-c2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ea-v0-c2-v1_reward/vocab.json
cycy233-l3-ea-v0-c2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-ea-v0-c2-v1_reward/tokenizer.json
cycy233-l3-ea-v0-c2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ea-v0-c2-v1_reward/reward.tensors
Job cycy233-l3-ea-v0-c2-v1-mkmlizer completed after 115.3s with status: succeeded
Stopping job with name cycy233-l3-ea-v0-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.13s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ea-v0-c2-v1
Waiting for inference service cycy233-l3-ea-v0-c2-v1 to be ready
Inference service cycy233-l3-ea-v0-c2-v1 ready after 40.43850111961365s
Pipeline stage ISVCDeployer completed in 47.45s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.370934247970581s
Received healthy response to inference request in 1.4804396629333496s
Received healthy response to inference request in 1.4530324935913086s
Received healthy response to inference request in 1.4230751991271973s
Received healthy response to inference request in 1.4971635341644287s
5 requests
0 failed requests
5th percentile: 1.4290666580200195
10th percentile: 1.4350581169128418
20th percentile: 1.4470410346984863
30th percentile: 1.4585139274597168
40th percentile: 1.4694767951965333
50th percentile: 1.4804396629333496
60th percentile: 1.4871292114257812
70th percentile: 1.493818759918213
80th percentile: 1.6719176769256594
90th percentile: 2.02142596244812
95th percentile: 2.1961801052093506
99th percentile: 2.335983419418335
mean time: 1.6449290275573731
Pipeline stage StressChecker completed in 8.92s
cycy233-l3-ea-v0-c2_v1 status is now deployed due to DeploymentManager action
cycy233-l3-ea-v0-c2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-ea-v0-c2_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-ea-v0-c2-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.89s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-ea-v0-c2-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ea-v0-c2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-ea-v0-c2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ea-v0-c2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ea-v0-c2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-ea-v0-c2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ea-v0-c2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-ea-v0-c2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-ea-v0-c2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ea-v0-c2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ea-v0-c2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ea-v0-c2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.29s
cycy233-l3-ea-v0-c2_v1 status is now torndown due to DeploymentManager action