developer_uid: Hastagaras
submission_id: hastagaras-l3-8b-dahlah-2_v1
model_name: hastagaras-l3-8b-dahlah-2_v1
model_group: Hastagaras/L3-8B-Dahlah-
status: torndown
timestamp: 2024-05-08T10:49:00+00:00
num_battles: 11348
num_wins: 5670
celo_rating: 1179.06
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-8B-Dahlah-2
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-l3-8b-dahlah-2_v1
is_internal_developer: False
language_model: Hastagaras/L3-8B-Dahlah-2
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-08
win_ratio: 0.4996475149806133
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '###'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "### Instruction:\nYou are `{bot_name}` and engage in an alternating Roleplay with `{user_name}`.\n\nOnly write {bot_name}'s next response with action and dialogue based on the provided context.\n\nYour persona as {bot_name}: {memory}\n\n", 'prompt_template': 'Your message example as {bot_name}: {prompt}\n\n', 'bot_template': '### Response:\n{bot_name}: {message}\n\n', 'user_template': '### Input:\n{user_name}: {message}\n\n', 'response_template': '### Response:\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 hastagaras-l3-8b-dahlah-2-v1-mkmlizer
Waiting for job on hastagaras-l3-8b-dahlah-2-v1-mkmlizer to finish
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-8b-dahlah-2-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-l3-8b-dahlah-2-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: Downloaded to shared memory in 27.989s
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  44%|████▍     | 129/291 [00:01<00:01, 127.99it/s]
Loading 0:  88%|████████▊ | 255/291 [00:02<00:00, 126.08it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 29.77it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: quantized model in 17.918s
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: Processed model Hastagaras/L3-8B-Dahlah-2 in 47.010s
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-8b-dahlah-2-v1
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-8b-dahlah-2-v1/special_tokens_map.json
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-8b-dahlah-2-v1/tokenizer_config.json
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-8b-dahlah-2-v1/config.json
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-8b-dahlah-2-v1/tokenizer.json
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-8b-dahlah-2-v1/flywheel_model.0.safetensors
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-8b-dahlah-2-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-l3-8b-dahlah-2-v1-mkmlizer:   warnings.warn(
hastagaras-l3-8b-dahlah-2-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-l3-8b-dahlah-2-v1-mkmlizer:   warnings.warn(
hastagaras-l3-8b-dahlah-2-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-l3-8b-dahlah-2-v1-mkmlizer:   warnings.warn(
hastagaras-l3-8b-dahlah-2-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-l3-8b-dahlah-2-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: Saving duration: 0.287s
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.668s
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-2-v1_reward
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-2-v1_reward/special_tokens_map.json
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-2-v1_reward/tokenizer_config.json
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-2-v1_reward/merges.txt
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-2-v1_reward/config.json
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-2-v1_reward/vocab.json
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-2-v1_reward/tokenizer.json
hastagaras-l3-8b-dahlah-2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-8b-dahlah-2-v1_reward/reward.tensors
Job hastagaras-l3-8b-dahlah-2-v1-mkmlizer completed after 72.78s with status: succeeded
Stopping job with name hastagaras-l3-8b-dahlah-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 73.58s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-8b-dahlah-2-v1
Waiting for inference service hastagaras-l3-8b-dahlah-2-v1 to be ready
Inference service hastagaras-l3-8b-dahlah-2-v1 ready after 30.221965074539185s
Pipeline stage ISVCDeployer completed in 36.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0555191040039062s
Received healthy response to inference request in 1.2326927185058594s
Received healthy response to inference request in 1.205733299255371s
Received healthy response to inference request in 1.2440576553344727s
Received healthy response to inference request in 1.2724294662475586s
5 requests
0 failed requests
5th percentile: 1.2111251831054688
10th percentile: 1.2165170669555665
20th percentile: 1.2273008346557617
30th percentile: 1.234965705871582
40th percentile: 1.2395116806030273
50th percentile: 1.2440576553344727
60th percentile: 1.255406379699707
70th percentile: 1.2667551040649414
80th percentile: 1.4290473937988282
90th percentile: 1.7422832489013673
95th percentile: 1.8989011764526367
99th percentile: 2.024195518493652
mean time: 1.4020864486694335
Pipeline stage StressChecker completed in 7.68s
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
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-l3-8b-dahlah-2_v1 status is now deployed due to DeploymentManager action
hastagaras-l3-8b-dahlah-2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-8b-dahlah-2_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-8b-dahlah-2-v1 is running
Tearing down inference service hastagaras-l3-8b-dahlah-2-v1
Toredown service hastagaras-l3-8b-dahlah-2-v1
Pipeline stage ISVCDeleter completed in 3.86s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-8b-dahlah-2-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-8b-dahlah-2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-8b-dahlah-2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-8b-dahlah-2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-8b-dahlah-2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-8b-dahlah-2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-8b-dahlah-2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-8b-dahlah-2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-8b-dahlah-2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-8b-dahlah-2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-8b-dahlah-2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-8b-dahlah-2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.92s
hastagaras-l3-8b-dahlah-2_v1 status is now torndown due to DeploymentManager action