developer_uid: Hastagaras
submission_id: hastagaras-anjir-8b-l3_v4
model_name: test3-2
model_group: Hastagaras/Anjir-8B-L3
status: torndown
timestamp: 2024-05-30T07:12:39+00:00
num_battles: 10876
num_wins: 6095
celo_rating: 1211.01
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Anjir-8B-L3
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: test3-2
is_internal_developer: False
language_model: Hastagaras/Anjir-8B-L3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-30
win_ratio: 0.5604082383229129
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 100, '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<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-anjir-8b-l3-v4-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-v4-mkmlizer to finish
hastagaras-anjir-8b-l3-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-v4-mkmlizer: ║     _____            __           __                                ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║       /___/                                                         ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║                                                                     ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║                                                                     ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║  belonging to:                                                      ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║                                                                     ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ║                                                                     ║
hastagaras-anjir-8b-l3-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-v4-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-anjir-8b-l3-v4-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-v4-mkmlizer: Downloaded to shared memory in 29.395s
hastagaras-anjir-8b-l3-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:17,  2.34s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:04,  4.25it/s]
Loading 0:  11%|█         | 32/291 [00:04<00:23, 10.94it/s]
Loading 0:  17%|█▋        | 50/291 [00:05<00:12, 20.00it/s]
Loading 0:  22%|██▏       | 64/291 [00:05<00:09, 23.64it/s]
Loading 0:  27%|██▋       | 78/291 [00:05<00:06, 32.62it/s]
Loading 0:  33%|███▎      | 95/291 [00:05<00:04, 46.34it/s]
Loading 0:  38%|███▊      | 112/291 [00:05<00:02, 61.65it/s]
Loading 0:  44%|████▍     | 128/291 [00:05<00:02, 76.47it/s]
Loading 0:  49%|████▉     | 143/291 [00:05<00:01, 88.36it/s]
Loading 0:  54%|█████▍    | 158/291 [00:06<00:01, 100.51it/s]
Loading 0:  59%|█████▉    | 173/291 [00:06<00:01, 69.48it/s] 
Loading 0:  64%|██████▍   | 186/291 [00:06<00:01, 78.86it/s]
Loading 0:  70%|██████▉   | 203/291 [00:06<00:00, 96.11it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 111.79it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 124.33it/s]
Loading 0:  87%|████████▋ | 253/291 [00:06<00:00, 130.51it/s]
Loading 0:  92%|█████████▏| 268/291 [00:07<00:00, 79.72it/s] 
Loading 0:  98%|█████████▊| 284/291 [00:07<00:00, 93.52it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-v4-mkmlizer: quantized model in 23.906s
hastagaras-anjir-8b-l3-v4-mkmlizer: Processed model Hastagaras/Anjir-8B-L3 in 55.992s
hastagaras-anjir-8b-l3-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v4
hastagaras-anjir-8b-l3-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v4/special_tokens_map.json
hastagaras-anjir-8b-l3-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v4/config.json
hastagaras-anjir-8b-l3-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v4/tokenizer_config.json
hastagaras-anjir-8b-l3-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v4/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-v4-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-anjir-8b-l3-v4-mkmlizer:   warnings.warn(
hastagaras-anjir-8b-l3-v4-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-anjir-8b-l3-v4-mkmlizer:   warnings.warn(
hastagaras-anjir-8b-l3-v4-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-anjir-8b-l3-v4-mkmlizer:   warnings.warn(
hastagaras-anjir-8b-l3-v4-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-anjir-8b-l3-v4-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-v4-mkmlizer: Saving duration: 0.460s
hastagaras-anjir-8b-l3-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.347s
hastagaras-anjir-8b-l3-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v4_reward
hastagaras-anjir-8b-l3-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v4_reward/config.json
hastagaras-anjir-8b-l3-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v4_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v4_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v4_reward/vocab.json
hastagaras-anjir-8b-l3-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v4_reward/merges.txt
hastagaras-anjir-8b-l3-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v4_reward/tokenizer.json
hastagaras-anjir-8b-l3-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v4_reward/reward.tensors
Job hastagaras-anjir-8b-l3-v4-mkmlizer completed after 82.95s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-v4-mkmlizer
Pipeline stage MKMLizer completed in 85.96s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-v4
Waiting for inference service hastagaras-anjir-8b-l3-v4 to be ready
Inference service hastagaras-anjir-8b-l3-v4 ready after 40.19878840446472s
Pipeline stage ISVCDeployer completed in 47.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1858816146850586s
Received healthy response to inference request in 1.3526837825775146s
Received healthy response to inference request in 1.3105010986328125s
Received healthy response to inference request in 1.2996160984039307s
Received healthy response to inference request in 1.224536418914795s
5 requests
0 failed requests
5th percentile: 1.2395523548126222
10th percentile: 1.2545682907104492
20th percentile: 1.2846001625061034
30th percentile: 1.301793098449707
40th percentile: 1.3061470985412598
50th percentile: 1.3105010986328125
60th percentile: 1.3273741722106933
70th percentile: 1.3442472457885741
80th percentile: 1.5193233489990237
90th percentile: 1.852602481842041
95th percentile: 2.01924204826355
99th percentile: 2.1525537014007567
mean time: 1.4746438026428224
Pipeline stage StressChecker completed in 8.05s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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-anjir-8b-l3_v4 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-anjir-8b-l3_v4
Running pipeline stage ISVCDeleter
Checking if service hastagaras-anjir-8b-l3-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.46s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-anjir-8b-l3-v4/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-anjir-8b-l3-v4_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.82s
hastagaras-anjir-8b-l3_v4 status is now torndown due to DeploymentManager action