hastagaras-meta-llama-3-_9278

developer_uid: Hastagaras

submission_id: hastagaras-meta-llama-3-_9278_v1

model_name: original-llama-with-anjir

model_group: Hastagaras/Meta-Llama-3-

status: torndown

timestamp: 2024-05-31T08:31:21+00:00

num_battles: 7045

num_wins: 3584

celo_rating: 1176.93

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/Meta-Llama-3-8B-Ins-ANJIR

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: original-llama-with-anjir

is_internal_developer: False

language_model: Hastagaras/Meta-Llama-3-8B-Ins-ANJIR

model_size: 8B

ranking_group: single

us_pacific_date: 2024-05-31

win_ratio: 0.5087295954577715

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, '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}

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-meta-llama-3-9278-v1-mkmlizer
Waiting for job on hastagaras-meta-llama-3-9278-v1-mkmlizer to finish
hastagaras-meta-llama-3-9278-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║                                                                     ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║                                                                     ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║                                                                     ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ║                                                                     ║
hastagaras-meta-llama-3-9278-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-meta-llama-3-9278-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-meta-llama-3-9278-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-meta-llama-3-9278-v1-mkmlizer: Downloaded to shared memory in 31.207s
hastagaras-meta-llama-3-9278-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-meta-llama-3-9278-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-meta-llama-3-9278-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 128.47it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:01, 150.45it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:01, 155.89it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 158.63it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:02, 83.35it/s] 
Loading 0:  34%|███▎      | 98/291 [00:00<00:02, 96.10it/s]
Loading 0:  39%|███▉      | 113/291 [00:01<00:01, 107.37it/s]
Loading 0:  45%|████▌     | 131/291 [00:01<00:01, 121.64it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:01, 133.19it/s]
Loading 0:  57%|█████▋    | 167/291 [00:01<00:00, 140.71it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 93.50it/s] 
Loading 0:  69%|██████▉   | 202/291 [00:01<00:00, 101.59it/s]
Loading 0:  76%|███████▌  | 220/291 [00:01<00:00, 115.71it/s]
Loading 0:  82%|████████▏ | 238/291 [00:02<00:00, 128.20it/s]
Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 138.43it/s]
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 146.69it/s]
Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 10.36it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-meta-llama-3-9278-v1-mkmlizer: quantized model in 22.872s
hastagaras-meta-llama-3-9278-v1-mkmlizer: Processed model Hastagaras/Meta-Llama-3-8B-Ins-ANJIR in 56.698s
hastagaras-meta-llama-3-9278-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-meta-llama-3-9278-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-meta-llama-3-9278-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-meta-llama-3-9278-v1
hastagaras-meta-llama-3-9278-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-meta-llama-3-9278-v1/config.json
hastagaras-meta-llama-3-9278-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-meta-llama-3-9278-v1/tokenizer_config.json
hastagaras-meta-llama-3-9278-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-meta-llama-3-9278-v1/special_tokens_map.json
hastagaras-meta-llama-3-9278-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-meta-llama-3-9278-v1/tokenizer.json
hastagaras-meta-llama-3-9278-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-meta-llama-3-9278-v1/flywheel_model.0.safetensors
hastagaras-meta-llama-3-9278-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-meta-llama-3-9278-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-meta-llama-3-9278-v1-mkmlizer:   warnings.warn(
hastagaras-meta-llama-3-9278-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-meta-llama-3-9278-v1-mkmlizer:   warnings.warn(
hastagaras-meta-llama-3-9278-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-meta-llama-3-9278-v1-mkmlizer:   warnings.warn(
hastagaras-meta-llama-3-9278-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-meta-llama-3-9278-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-meta-llama-3-9278-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-meta-llama-3-9278-v1-mkmlizer: Saving duration: 0.400s
hastagaras-meta-llama-3-9278-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.440s
hastagaras-meta-llama-3-9278-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-meta-llama-3-9278-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-meta-llama-3-9278-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v1_reward
hastagaras-meta-llama-3-9278-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v1_reward/tokenizer_config.json
hastagaras-meta-llama-3-9278-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v1_reward/vocab.json
hastagaras-meta-llama-3-9278-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v1_reward/merges.txt
hastagaras-meta-llama-3-9278-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v1_reward/config.json
hastagaras-meta-llama-3-9278-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v1_reward/special_tokens_map.json
hastagaras-meta-llama-3-9278-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v1_reward/tokenizer.json
Job hastagaras-meta-llama-3-9278-v1-mkmlizer completed after 82.91s with status: succeeded
Stopping job with name hastagaras-meta-llama-3-9278-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.60s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-meta-llama-3-9278-v1
Waiting for inference service hastagaras-meta-llama-3-9278-v1 to be ready
Inference service hastagaras-meta-llama-3-9278-v1 ready after 30.17529845237732s
Pipeline stage ISVCDeployer completed in 35.93s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1973724365234375s
Received healthy response to inference request in 1.3336713314056396s
Received healthy response to inference request in 1.2955577373504639s
Received healthy response to inference request in 1.288956880569458s
Received healthy response to inference request in 1.2476000785827637s
5 requests
0 failed requests
5th percentile: 1.2558714389801025
10th percentile: 1.2641427993774415
20th percentile: 1.2806855201721192
30th percentile: 1.2902770519256592
40th percentile: 1.2929173946380614
50th percentile: 1.2955577373504639
60th percentile: 1.3108031749725342
70th percentile: 1.3260486125946045
80th percentile: 1.5064115524291994
90th percentile: 1.8518919944763184
95th percentile: 2.024632215499878
99th percentile: 2.1628243923187256
mean time: 1.4726316928863525
Pipeline stage StressChecker completed in 8.07s
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-meta-llama-3-_9278_v1 status is now deployed due to DeploymentManager action
hastagaras-meta-llama-3-_9278_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-meta-llama-3-_9278_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-meta-llama-3-9278-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.22s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-meta-llama-3-9278-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-meta-llama-3-9278-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-meta-llama-3-9278-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-meta-llama-3-9278-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-meta-llama-3-9278-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-meta-llama-3-9278-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-meta-llama-3-9278-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-meta-llama-3-9278-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-meta-llama-3-9278-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-meta-llama-3-9278-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-meta-llama-3-9278-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-meta-llama-3-9278-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.49s
hastagaras-meta-llama-3-_9278_v1 status is now torndown due to DeploymentManager action