developer_uid: v000000
submission_id: v000000-l3-8b-serpentine_v1
model_name: v000000-l3-8b-serpentine_v1
model_group: v000000/L3-8B-Serpentine
status: torndown
timestamp: 2024-06-13T01:40:08+00:00
num_battles: 35461
num_wins: 19088
celo_rating: 1207.25
family_friendly_score: 0.0
submission_type: basic
model_repo: v000000/L3-8B-Serpentine
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: v000000-l3-8b-serpentine_v1
is_internal_developer: False
language_model: v000000/L3-8B-Serpentine
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-12
win_ratio: 0.5382814923437015
generation_params: {'temperature': 1.22, 'top_p': 0.95, 'min_p': 0.08, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_of_text|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name v000000-l3-8b-serpentine-v1-mkmlizer
Waiting for job on v000000-l3-8b-serpentine-v1-mkmlizer to finish
v000000-l3-8b-serpentine-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-l3-8b-serpentine-v1-mkmlizer: ║     _____            __           __                                ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║       /___/                                                         ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║                                                                     ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║  https://mk1.ai                                                     ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║                                                                     ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║  belonging to:                                                      ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║                                                                     ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║  Chai Research Corp.                                                ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
v000000-l3-8b-serpentine-v1-mkmlizer: ║                                                                     ║
v000000-l3-8b-serpentine-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-l3-8b-serpentine-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
v000000-l3-8b-serpentine-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
v000000-l3-8b-serpentine-v1-mkmlizer: Downloaded to shared memory in 17.942s
v000000-l3-8b-serpentine-v1-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-l3-8b-serpentine-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-l3-8b-serpentine-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<13:00,  2.70s/it]
Loading 0:   5%|▌         | 15/291 [00:05<01:14,  3.70it/s]
Loading 0:  11%|█         | 32/291 [00:05<00:27,  9.56it/s]
Loading 0:  17%|█▋        | 49/291 [00:05<00:14, 17.21it/s]
Loading 0:  21%|██▏       | 62/291 [00:06<00:11, 19.23it/s]
Loading 0:  27%|██▋       | 78/291 [00:06<00:07, 28.43it/s]
Loading 0:  33%|███▎      | 95/291 [00:06<00:04, 40.69it/s]
Loading 0:  39%|███▉      | 113/291 [00:06<00:03, 55.36it/s]
Loading 0:  45%|████▌     | 131/291 [00:06<00:02, 70.84it/s]
Loading 0:  51%|█████     | 148/291 [00:06<00:01, 86.10it/s]
Loading 0:  56%|█████▋    | 164/291 [00:06<00:01, 99.23it/s]
Loading 0:  62%|██████▏   | 180/291 [00:07<00:01, 64.86it/s]
Loading 0:  67%|██████▋   | 195/291 [00:07<00:01, 75.72it/s]
Loading 0:  73%|███████▎  | 212/291 [00:07<00:00, 91.26it/s]
Loading 0:  79%|███████▊  | 229/291 [00:07<00:00, 105.28it/s]
Loading 0:  84%|████████▍ | 244/291 [00:07<00:00, 114.22it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 120.17it/s]
Loading 0:  94%|█████████▍| 274/291 [00:08<00:00, 73.30it/s] 
Loading 0:  99%|█████████▉| 288/291 [00:08<00:00, 83.95it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
v000000-l3-8b-serpentine-v1-mkmlizer: quantized model in 20.613s
v000000-l3-8b-serpentine-v1-mkmlizer: Processed model v000000/L3-8B-Serpentine in 39.682s
v000000-l3-8b-serpentine-v1-mkmlizer: creating bucket guanaco-mkml-models
v000000-l3-8b-serpentine-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-l3-8b-serpentine-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-l3-8b-serpentine-v1
v000000-l3-8b-serpentine-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-l3-8b-serpentine-v1/config.json
v000000-l3-8b-serpentine-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-l3-8b-serpentine-v1/special_tokens_map.json
v000000-l3-8b-serpentine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-l3-8b-serpentine-v1/tokenizer_config.json
v000000-l3-8b-serpentine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-l3-8b-serpentine-v1/tokenizer.json
v000000-l3-8b-serpentine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-l3-8b-serpentine-v1/flywheel_model.0.safetensors
v000000-l3-8b-serpentine-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-l3-8b-serpentine-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
v000000-l3-8b-serpentine-v1-mkmlizer:   warnings.warn(
v000000-l3-8b-serpentine-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
v000000-l3-8b-serpentine-v1-mkmlizer:   warnings.warn(
v000000-l3-8b-serpentine-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
v000000-l3-8b-serpentine-v1-mkmlizer:   warnings.warn(
Failed to get response for submission blend_junes_2024-06-13: name 'requests' is not defined
v000000-l3-8b-serpentine-v1-mkmlizer: Saving duration: 0.252s
v000000-l3-8b-serpentine-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.540s
v000000-l3-8b-serpentine-v1-mkmlizer: creating bucket guanaco-reward-models
v000000-l3-8b-serpentine-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-l3-8b-serpentine-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-l3-8b-serpentine-v1_reward
v000000-l3-8b-serpentine-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-l3-8b-serpentine-v1_reward/config.json
v000000-l3-8b-serpentine-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/v000000-l3-8b-serpentine-v1_reward/tokenizer_config.json
v000000-l3-8b-serpentine-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-l3-8b-serpentine-v1_reward/special_tokens_map.json
v000000-l3-8b-serpentine-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-l3-8b-serpentine-v1_reward/merges.txt
v000000-l3-8b-serpentine-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-l3-8b-serpentine-v1_reward/vocab.json
v000000-l3-8b-serpentine-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/v000000-l3-8b-serpentine-v1_reward/tokenizer.json
v000000-l3-8b-serpentine-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/v000000-l3-8b-serpentine-v1_reward/reward.tensors
Job v000000-l3-8b-serpentine-v1-mkmlizer completed after 63.32s with status: succeeded
Stopping job with name v000000-l3-8b-serpentine-v1-mkmlizer
Pipeline stage MKMLizer completed in 68.84s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service v000000-l3-8b-serpentine-v1
Waiting for inference service v000000-l3-8b-serpentine-v1 to be ready
Inference service v000000-l3-8b-serpentine-v1 ready after 40.22606182098389s
Pipeline stage ISVCDeployer completed in 48.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2298381328582764s
Received healthy response to inference request in 1.3700292110443115s
Received healthy response to inference request in 1.3319225311279297s
Received healthy response to inference request in 1.2882118225097656s
Received healthy response to inference request in 1.2464447021484375s
5 requests
0 failed requests
5th percentile: 1.254798126220703
10th percentile: 1.2631515502929687
20th percentile: 1.2798583984375
30th percentile: 1.2969539642333985
40th percentile: 1.314438247680664
50th percentile: 1.3319225311279297
60th percentile: 1.3471652030944825
70th percentile: 1.3624078750610351
80th percentile: 1.5419909954071047
90th percentile: 1.8859145641326904
95th percentile: 2.0578763484954834
99th percentile: 2.1954457759857178
mean time: 1.4932892799377442
Pipeline stage StressChecker completed in 8.15s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
v000000-l3-8b-serpentine_v1 status is now deployed due to DeploymentManager action
v000000-l3-8b-serpentine_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of v000000-l3-8b-serpentine_v1
Running pipeline stage ISVCDeleter
Checking if service v000000-l3-8b-serpentine-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.95s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key v000000-l3-8b-serpentine-v1/config.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-serpentine-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-serpentine-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-serpentine-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-serpentine-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key v000000-l3-8b-serpentine-v1_reward/config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpentine-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpentine-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpentine-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpentine-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpentine-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpentine-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.26s
v000000-l3-8b-serpentine_v1 status is now torndown due to DeploymentManager action