developer_uid: Hastagaras
submission_id: hastagaras-l3-cokelat-8b_v1
model_name: hastagaras-l3-cokelat-8b_v1
model_group: Hastagaras/L3-Cokelat-8B
status: torndown
timestamp: 2024-04-26T09:51:00+00:00
num_battles: 9335
num_wins: 5212
celo_rating: 1191.29
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-Cokelat-8B
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: hastagaras-l3-cokelat-8b_v1
is_internal_developer: False
language_model: Hastagaras/L3-Cokelat-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-26
win_ratio: 0.5583288698446706
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '###', ']'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n\nEngage in a roleplay as {bot_name} and write {bot_name}'s next response with genuine feelings and emotions based on the below input.\n\n### Input:\n\n{memory}\n\nLet's start the roleplay, write inside square brackets.", 'prompt_template': "\n\n### Response:\nOkay!, I'll start the roleplay with my genuine feelings and emotions as {bot_name}.\n\n[{bot_name}: {prompt}]<|end_of_text|>", 'bot_template': '\n\n### Response:\n[{bot_name}: {message}]<|end_of_text|>', 'user_template': '\n\n### Input:\n[{user_name}: {message}]', 'response_template': '\n\n### Response:\nHmm, below is my response:\n\n[{bot_name}:', 'truncate_by_message': False}
model_eval_status: success
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 hastagaras-l3-cokelat-8b-v1-mkmlizer
Waiting for job on hastagaras-l3-cokelat-8b-v1-mkmlizer to finish
hastagaras-l3-cokelat-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-cokelat-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-cokelat-8b-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.
hastagaras-l3-cokelat-8b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-cokelat-8b-v1-mkmlizer: Downloaded to shared memory in 28.282s
hastagaras-l3-cokelat-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-cokelat-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-cokelat-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:03<09:29,  1.97s/it]
Loading 0:  42%|████▏     | 122/291 [00:05<00:05, 30.80it/s]
Loading 0:  98%|█████████▊| 284/291 [00:06<00:00, 62.97it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-cokelat-8b-v1-mkmlizer: quantized model in 17.078s
hastagaras-l3-cokelat-8b-v1-mkmlizer: Processed model Hastagaras/L3-Cokelat-8B in 46.342s
hastagaras-l3-cokelat-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-cokelat-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-cokelat-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-cokelat-8b-v1
hastagaras-l3-cokelat-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-cokelat-8b-v1/config.json
hastagaras-l3-cokelat-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-cokelat-8b-v1/special_tokens_map.json
hastagaras-l3-cokelat-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-cokelat-8b-v1/tokenizer_config.json
hastagaras-l3-cokelat-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-cokelat-8b-v1/tokenizer.json
hastagaras-l3-cokelat-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-cokelat-8b-v1/flywheel_model.0.safetensors
hastagaras-l3-cokelat-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-cokelat-8b-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.
hastagaras-l3-cokelat-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-cokelat-8b-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.
hastagaras-l3-cokelat-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-cokelat-8b-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.
hastagaras-l3-cokelat-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-cokelat-8b-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
hastagaras-l3-cokelat-8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-cokelat-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-cokelat-8b-v1-mkmlizer: Saving duration: 0.259s
hastagaras-l3-cokelat-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.822s
hastagaras-l3-cokelat-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-cokelat-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-cokelat-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-cokelat-8b-v1_reward
hastagaras-l3-cokelat-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-cokelat-8b-v1_reward/special_tokens_map.json
hastagaras-l3-cokelat-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-cokelat-8b-v1_reward/merges.txt
hastagaras-l3-cokelat-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-cokelat-8b-v1_reward/tokenizer_config.json
hastagaras-l3-cokelat-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-cokelat-8b-v1_reward/config.json
hastagaras-l3-cokelat-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-cokelat-8b-v1_reward/vocab.json
hastagaras-l3-cokelat-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-cokelat-8b-v1_reward/tokenizer.json
hastagaras-l3-cokelat-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-cokelat-8b-v1_reward/reward.tensors
Job hastagaras-l3-cokelat-8b-v1-mkmlizer completed after 73.19s with status: succeeded
Stopping job with name hastagaras-l3-cokelat-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 78.39s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-cokelat-8b-v1
Waiting for inference service hastagaras-l3-cokelat-8b-v1 to be ready
Inference service hastagaras-l3-cokelat-8b-v1 ready after 30.17157483100891s
Pipeline stage ISVCDeployer completed in 37.19s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1683189868927s
Received healthy response to inference request in 1.312913417816162s
Received healthy response to inference request in 1.4021601676940918s
Received healthy response to inference request in 1.30287766456604s
Received healthy response to inference request in 1.26847243309021s
5 requests
0 failed requests
5th percentile: 1.275353479385376
10th percentile: 1.282234525680542
20th percentile: 1.295996618270874
30th percentile: 1.3048848152160644
40th percentile: 1.3088991165161132
50th percentile: 1.312913417816162
60th percentile: 1.348612117767334
70th percentile: 1.384310817718506
80th percentile: 1.5553919315338136
90th percentile: 1.861855459213257
95th percentile: 2.015087223052978
99th percentile: 2.1376726341247556
mean time: 1.490948534011841
Pipeline stage StressChecker completed in 8.20s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-l3-cokelat-8b_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-l3-cokelat-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-cokelat-8b_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-cokelat-8b-v1 is running
Tearing down inference service hastagaras-l3-cokelat-8b-v1
Toredown service hastagaras-l3-cokelat-8b-v1
Pipeline stage ISVCDeleter completed in 3.41s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-cokelat-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-cokelat-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-cokelat-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-cokelat-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-cokelat-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-cokelat-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cokelat-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-cokelat-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-cokelat-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cokelat-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cokelat-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-cokelat-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.92s
hastagaras-l3-cokelat-8b_v1 status is now torndown due to DeploymentManager action