cycy233-l3-bdpo-v9-c1

developer_uid: shiroe40

submission_id: cycy233-l3-bdpo-v9-c1_v2

model_name: auto

model_group: cycy233/L3-bdpo-v9-c1

status: torndown

timestamp: 2024-07-16T02:06:36+00:00

num_battles: 165000

num_wins: 80789

celo_rating: 1205.08

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/L3-bdpo-v9-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-bdpo-v9-c1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-15

win_ratio: 0.489630303030303

generation_params: {'temperature': 0.6, '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-bdpo-v9-c1-v2-mkmlizer
Waiting for job on cycy233-l3-bdpo-v9-c1-v2-mkmlizer to finish
Stopping job with name cycy233-l3-bdpo-v9-c1-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name cycy233-l3-bdpo-v9-c1-v2-mkmlizer
Waiting for job on cycy233-l3-bdpo-v9-c1-v2-mkmlizer to finish
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║       /___/                                                         ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║  Version: 0.9.5.post2                                               ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: Downloaded to shared memory in 30.614s
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: lm_head.weight torch.Size([139542528])
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: model.layers.31.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: model.layers.31.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: model.layers.31.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: model.norm.weight torch.Size([4096])
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bdpo-v9-c1-v2/flywheel_model.0.safetensors
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-bdpo-v9-c1-v2-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-bdpo-v9-c1-v2-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v9-c1-v2-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-bdpo-v9-c1-v2-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v9-c1-v2-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-bdpo-v9-c1-v2-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: Saving duration: 2.276s
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 13.745s
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bdpo-v9-c1-v2_reward
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v9-c1-v2_reward/config.json
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v9-c1-v2_reward/tokenizer_config.json
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bdpo-v9-c1-v2_reward/merges.txt
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bdpo-v9-c1-v2_reward/vocab.json
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bdpo-v9-c1-v2_reward/special_tokens_map.json
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bdpo-v9-c1-v2_reward/tokenizer.json
cycy233-l3-bdpo-v9-c1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bdpo-v9-c1-v2_reward/reward.tensors
Job cycy233-l3-bdpo-v9-c1-v2-mkmlizer completed after 103.88s with status: succeeded
Stopping job with name cycy233-l3-bdpo-v9-c1-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.38s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bdpo-v9-c1-v2
Waiting for inference service cycy233-l3-bdpo-v9-c1-v2 to be ready
Inference service cycy233-l3-bdpo-v9-c1-v2 ready after 50.2508327960968s
Pipeline stage ISVCDeployer completed in 57.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.307286024093628s
Received healthy response to inference request in 1.7318384647369385s
Received healthy response to inference request in 1.455273151397705s
Received healthy response to inference request in 1.4341275691986084s
Received healthy response to inference request in 1.4778740406036377s
5 requests
0 failed requests
5th percentile: 1.4383566856384278
10th percentile: 1.4425858020782472
20th percentile: 1.4510440349578857
30th percentile: 1.4597933292388916
40th percentile: 1.4688336849212646
50th percentile: 1.4778740406036377
60th percentile: 1.579459810256958
70th percentile: 1.6810455799102784
80th percentile: 1.8469279766082765
90th percentile: 2.077107000350952
95th percentile: 2.19219651222229
99th percentile: 2.2842681217193603
mean time: 1.6812798500061035
Pipeline stage StressChecker completed in 9.13s
cycy233-l3-bdpo-v9-c1_v2 status is now deployed due to DeploymentManager action
cycy233-l3-bdpo-v9-c1_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-bdpo-v9-c1_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-bdpo-v9-c1-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.17s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-bdpo-v9-c1-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v9-c1-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v9-c1-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v9-c1-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v9-c1-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-bdpo-v9-c1-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v9-c1-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v9-c1-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v9-c1-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v9-c1-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v9-c1-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v9-c1-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.75s
cycy233-l3-bdpo-v9-c1_v2 status is now torndown due to DeploymentManager action