developer_uid: Hastagaras
submission_id: hastagaras-meta-llama-3-_9278_v2
model_name: original-llama-with-anjir
model_group: Hastagaras/Meta-Llama-3-
status: torndown
timestamp: 2024-05-31T08:34:24+00:00
num_battles: 15264
num_wins: 7931
celo_rating: 1182.48
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: 0.51958857442348
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': "<|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-v2-mkmlizer
Waiting for job on hastagaras-meta-llama-3-9278-v2-mkmlizer to finish
hastagaras-meta-llama-3-9278-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║                                                                     ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║                                                                     ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║                                                                     ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ║                                                                     ║
hastagaras-meta-llama-3-9278-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-meta-llama-3-9278-v2-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-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-meta-llama-3-9278-v2-mkmlizer: Downloaded to shared memory in 20.644s
hastagaras-meta-llama-3-9278-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-meta-llama-3-9278-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-meta-llama-3-9278-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 125.96it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:01, 145.40it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:01, 153.41it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 157.46it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:02, 82.93it/s] 
Loading 0:  33%|███▎      | 95/291 [00:00<00:02, 90.29it/s]
Loading 0:  39%|███▉      | 113/291 [00:01<00:01, 107.51it/s]
Loading 0:  45%|████▌     | 131/291 [00:01<00:01, 122.20it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:01, 133.99it/s]
Loading 0:  57%|█████▋    | 167/291 [00:01<00:00, 142.95it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 95.98it/s] 
Loading 0:  69%|██████▉   | 201/291 [00:01<00:00, 103.57it/s]
Loading 0:  74%|███████▍  | 215/291 [00:01<00:00, 110.93it/s]
Loading 0:  79%|███████▉  | 230/291 [00:01<00:00, 119.14it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 128.68it/s]
Loading 0:  90%|█████████ | 262/291 [00:02<00:00, 132.20it/s]
Loading 0:  95%|█████████▌| 277/291 [00:02<00:00, 133.98it/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-v2-mkmlizer: quantized model in 23.152s
hastagaras-meta-llama-3-9278-v2-mkmlizer: Processed model Hastagaras/Meta-Llama-3-8B-Ins-ANJIR in 46.376s
hastagaras-meta-llama-3-9278-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-meta-llama-3-9278-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-meta-llama-3-9278-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-meta-llama-3-9278-v2
hastagaras-meta-llama-3-9278-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-meta-llama-3-9278-v2/config.json
hastagaras-meta-llama-3-9278-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-meta-llama-3-9278-v2/special_tokens_map.json
hastagaras-meta-llama-3-9278-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-meta-llama-3-9278-v2/tokenizer_config.json
hastagaras-meta-llama-3-9278-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-meta-llama-3-9278-v2/tokenizer.json
hastagaras-meta-llama-3-9278-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-meta-llama-3-9278-v2/flywheel_model.0.safetensors
hastagaras-meta-llama-3-9278-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-meta-llama-3-9278-v2-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-v2-mkmlizer:   warnings.warn(
hastagaras-meta-llama-3-9278-v2-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-v2-mkmlizer:   warnings.warn(
hastagaras-meta-llama-3-9278-v2-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-v2-mkmlizer:   warnings.warn(
hastagaras-meta-llama-3-9278-v2-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-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-meta-llama-3-9278-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-meta-llama-3-9278-v2-mkmlizer: Saving duration: 0.399s
hastagaras-meta-llama-3-9278-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.612s
hastagaras-meta-llama-3-9278-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-meta-llama-3-9278-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-meta-llama-3-9278-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v2_reward
hastagaras-meta-llama-3-9278-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v2_reward/special_tokens_map.json
hastagaras-meta-llama-3-9278-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v2_reward/config.json
hastagaras-meta-llama-3-9278-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v2_reward/tokenizer_config.json
hastagaras-meta-llama-3-9278-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v2_reward/vocab.json
hastagaras-meta-llama-3-9278-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v2_reward/merges.txt
hastagaras-meta-llama-3-9278-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v2_reward/tokenizer.json
hastagaras-meta-llama-3-9278-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-meta-llama-3-9278-v2_reward/reward.tensors
Job hastagaras-meta-llama-3-9278-v2-mkmlizer completed after 73.32s with status: succeeded
Stopping job with name hastagaras-meta-llama-3-9278-v2-mkmlizer
Pipeline stage MKMLizer completed in 77.03s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-meta-llama-3-9278-v2
Waiting for inference service hastagaras-meta-llama-3-9278-v2 to be ready
Inference service hastagaras-meta-llama-3-9278-v2 ready after 40.23511290550232s
Pipeline stage ISVCDeployer completed in 47.62s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2866954803466797s
Received healthy response to inference request in 1.3579583168029785s
Received healthy response to inference request in 1.3031542301177979s
Received healthy response to inference request in 1.29667329788208s
Received healthy response to inference request in 1.2343764305114746s
5 requests
0 failed requests
5th percentile: 1.2468358039855958
10th percentile: 1.2592951774597168
20th percentile: 1.284213924407959
30th percentile: 1.2979694843292235
40th percentile: 1.3005618572235107
50th percentile: 1.3031542301177979
60th percentile: 1.3250758647918701
70th percentile: 1.3469974994659424
80th percentile: 1.543705749511719
90th percentile: 1.9152006149291994
95th percentile: 2.100948047637939
99th percentile: 2.2495459938049316
mean time: 1.495771551132202
Pipeline stage StressChecker completed in 8.08s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
hastagaras-meta-llama-3-_9278_v2 status is now deployed due to DeploymentManager action
hastagaras-meta-llama-3-_9278_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-meta-llama-3-_9278_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-meta-llama-3-9278-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.34s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-meta-llama-3-9278-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-meta-llama-3-9278-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-meta-llama-3-9278-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-meta-llama-3-9278-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-meta-llama-3-9278-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-meta-llama-3-9278-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-meta-llama-3-9278-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-meta-llama-3-9278-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-meta-llama-3-9278-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-meta-llama-3-9278-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-meta-llama-3-9278-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-meta-llama-3-9278-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.56s
hastagaras-meta-llama-3-_9278_v2 status is now torndown due to DeploymentManager action