developer_uid: Hastagaras
submission_id: hastagaras-jamet-8b-l3-m_953_v1
model_name: alignment-test
model_group: Hastagaras/Jamet-8B-L3-M
status: torndown
timestamp: 2024-06-06T03:07:17+00:00
num_battles: 25499
num_wins: 13749
celo_rating: 1203.02
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Jamet-8B-L3-MK.1-ST
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: alignment-test
is_internal_developer: False
language_model: Hastagaras/Jamet-8B-L3-MK.1-ST
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-05
win_ratio: 0.5391976155927684
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, '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': "<|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\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-jamet-8b-l3-m-953-v1-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-953-v1-mkmlizer to finish
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║                                                                     ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║                                                                     ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║                                                                     ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ║                                                                     ║
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-953-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-jamet-8b-l3-m-953-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: Downloaded to shared memory in 36.226s
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:06,  2.31s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:03,  4.32it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:22, 11.46it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 20.62it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:09, 24.93it/s]
Loading 0:  27%|██▋       | 80/291 [00:05<00:06, 35.06it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 47.70it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 63.96it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 80.69it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 96.09it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 75.10it/s]
Loading 0:  62%|██████▏   | 180/291 [00:06<00:01, 85.22it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:01, 91.16it/s]
Loading 0:  73%|███████▎  | 211/291 [00:06<00:00, 106.31it/s]
Loading 0:  79%|███████▊  | 229/291 [00:06<00:00, 120.87it/s]
Loading 0:  85%|████████▍ | 247/291 [00:06<00:00, 132.72it/s]
Loading 0:  90%|█████████ | 263/291 [00:06<00:00, 139.01it/s]
Loading 0:  96%|█████████▌| 279/291 [00:07<00:00, 85.54it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: quantized model in 23.519s
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.1-ST in 62.403s
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-953-v1
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-953-v1/tokenizer_config.json
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-953-v1/config.json
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-953-v1/special_tokens_map.json
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-953-v1/tokenizer.json
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-953-v1/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-953-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-jamet-8b-l3-m-953-v1-mkmlizer:   warnings.warn(
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-953-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-jamet-8b-l3-m-953-v1-mkmlizer:   warnings.warn(
hastagaras-jamet-8b-l3-m-953-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-jamet-8b-l3-m-953-v1-mkmlizer:   warnings.warn(
hastagaras-jamet-8b-l3-m-953-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-jamet-8b-l3-m-953-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: Saving duration: 0.394s
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.377s
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-953-v1_reward
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-953-v1_reward/config.json
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-953-v1_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-953-v1_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-953-v1_reward/merges.txt
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-953-v1_reward/vocab.json
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-953-v1_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-953-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-953-v1_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-953-v1-mkmlizer completed after 93.73s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-953-v1-mkmlizer
Pipeline stage MKMLizer completed in 97.84s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-953-v1
Waiting for inference service hastagaras-jamet-8b-l3-m-953-v1 to be ready
Inference service hastagaras-jamet-8b-l3-m-953-v1 ready after 30.172088384628296s
Pipeline stage ISVCDeployer completed in 37.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0971813201904297s
Received healthy response to inference request in 1.359114646911621s
Received healthy response to inference request in 1.3164570331573486s
Received healthy response to inference request in 1.3007280826568604s
Received healthy response to inference request in 1.2794339656829834s
5 requests
0 failed requests
5th percentile: 1.2836927890777587
10th percentile: 1.287951612472534
20th percentile: 1.296469259262085
30th percentile: 1.303873872756958
40th percentile: 1.3101654529571534
50th percentile: 1.3164570331573486
60th percentile: 1.3335200786590575
70th percentile: 1.3505831241607666
80th percentile: 1.5067279815673829
90th percentile: 1.8019546508789064
95th percentile: 1.949567985534668
99th percentile: 2.067658653259277
mean time: 1.4705830097198487
Pipeline stage StressChecker completed in 8.06s
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
hastagaras-jamet-8b-l3-m_953_v1 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_953_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-jamet-8b-l3-m_953_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-jamet-8b-l3-m-953-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.74s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-jamet-8b-l3-m-953-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-953-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-953-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-953-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-953-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-jamet-8b-l3-m-953-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-953-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-953-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-953-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-953-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-953-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-953-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.72s
hastagaras-jamet-8b-l3-m_953_v1 status is now torndown due to DeploymentManager action