developer_uid: Hastagaras
submission_id: hastagaras-llama-3-8b-o128_v2
model_name: moarrrr
model_group: Hastagaras/llama-3-8b-o1
status: torndown
timestamp: 2024-05-14T23:48:35+00:00
num_battles: 10185
num_wins: 5297
celo_rating: 1194.77
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/llama-3-8b-o128
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: moarrrr
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-o128
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-14
win_ratio: 0.5200785468826706
generation_params: {'temperature': 1.0, 'top_p': 1.0, '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': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this uncensored roleplay chat between {user_name} and {bot_name}. Always write your response as {bot_name} based on the following description.\n\nDescription: {memory}\n", 'prompt_template': 'Previously: {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: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-o128-v2-mkmlizer
Waiting for job on hastagaras-llama-3-8b-o128-v2-mkmlizer to finish
hastagaras-llama-3-8b-o128-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-o128-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-o128-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-llama-3-8b-o128-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-o128-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:01, 201.27it/s]
Loading 0:  15%|█▌        | 45/291 [00:00<00:01, 215.78it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 211.22it/s]
Loading 0:  31%|███       | 89/291 [00:00<00:02, 95.81it/s] 
Loading 0:  38%|███▊      | 111/291 [00:00<00:01, 118.66it/s]
Loading 0:  45%|████▍     | 130/291 [00:00<00:01, 132.41it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:00, 144.80it/s]
Loading 0:  59%|█████▉    | 171/291 [00:01<00:00, 162.41it/s]
Loading 0:  65%|██████▌   | 190/291 [00:01<00:01, 95.62it/s] 
Loading 0:  72%|███████▏  | 210/291 [00:01<00:00, 113.55it/s]
Loading 0:  79%|███████▉  | 230/291 [00:01<00:00, 128.23it/s]
Loading 0:  88%|████████▊ | 255/291 [00:01<00:00, 151.07it/s]
Loading 0:  95%|█████████▍| 275/291 [00:01<00:00, 159.72it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-o128-v2-mkmlizer: quantized model in 17.111s
hastagaras-llama-3-8b-o128-v2-mkmlizer: Processed model Hastagaras/llama-3-8b-o128 in 32.886s
hastagaras-llama-3-8b-o128-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-o128-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-o128-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-o128-v2
hastagaras-llama-3-8b-o128-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-o128-v2/config.json
hastagaras-llama-3-8b-o128-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-o128-v2/special_tokens_map.json
hastagaras-llama-3-8b-o128-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-o128-v2/tokenizer_config.json
hastagaras-llama-3-8b-o128-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-o128-v2/tokenizer.json
hastagaras-llama-3-8b-o128-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-o128-v2/flywheel_model.0.safetensors
hastagaras-llama-3-8b-o128-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-o128-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-llama-3-8b-o128-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-o128-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-llama-3-8b-o128-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-o128-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-llama-3-8b-o128-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-o128-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-llama-3-8b-o128-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-o128-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-o128-v2-mkmlizer: Saving duration: 0.236s
hastagaras-llama-3-8b-o128-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.439s
hastagaras-llama-3-8b-o128-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-o128-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-o128-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v2_reward
hastagaras-llama-3-8b-o128-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v2_reward/config.json
hastagaras-llama-3-8b-o128-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v2_reward/special_tokens_map.json
hastagaras-llama-3-8b-o128-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v2_reward/tokenizer_config.json
hastagaras-llama-3-8b-o128-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v2_reward/vocab.json
hastagaras-llama-3-8b-o128-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v2_reward/merges.txt
hastagaras-llama-3-8b-o128-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v2_reward/tokenizer.json
hastagaras-llama-3-8b-o128-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v2_reward/reward.tensors
Job hastagaras-llama-3-8b-o128-v2-mkmlizer completed after 63.88s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-o128-v2-mkmlizer
Pipeline stage MKMLizer completed in 68.25s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-o128-v2
Waiting for inference service hastagaras-llama-3-8b-o128-v2 to be ready
Inference service hastagaras-llama-3-8b-o128-v2 ready after 30.211374044418335s
Pipeline stage ISVCDeployer completed in 37.80s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2084801197052s
Received healthy response to inference request in 1.3134956359863281s
Received healthy response to inference request in 1.3588712215423584s
Received healthy response to inference request in 1.334097146987915s
Received healthy response to inference request in 1.3040833473205566s
5 requests
0 failed requests
5th percentile: 1.3059658050537108
10th percentile: 1.3078482627868653
20th percentile: 1.311613178253174
30th percentile: 1.3176159381866455
40th percentile: 1.3258565425872804
50th percentile: 1.334097146987915
60th percentile: 1.3440067768096924
70th percentile: 1.3539164066314697
80th percentile: 1.528793001174927
90th percentile: 1.8686365604400637
95th percentile: 2.0385583400726315
99th percentile: 2.1744957637786864
mean time: 1.5038054943084718
Pipeline stage StressChecker completed in 8.12s
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
hastagaras-llama-3-8b-o128_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama-3-8b-o128_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-o128_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-o128-v2 is running
admin requested tearing down of hastagaras-llama-3-8b-o128_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-o128-v3 is running
Tearing down inference service hastagaras-llama-3-8b-o128-v3
Tearing down inference service hastagaras-llama-3-8b-o128-v2
Toredown service hastagaras-llama-3-8b-o128-v3
Toredown service hastagaras-llama-3-8b-o128-v2
Pipeline stage ISVCDeleter completed in 5.38s
Running pipeline stage MKMLModelDeleter
Pipeline stage ISVCDeleter completed in 5.99s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-o128-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-o128-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-o128-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-o128-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Deleting key hastagaras-llama-3-8b-o128-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-o128-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-o128-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-o128-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-o128-v3/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-o128-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-o128-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v3_reward/vocab.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.00s
Pipeline stage MKMLModelDeleter completed in 2.94s
hastagaras-llama-3-8b-o128_v3 status is now torndown due to DeploymentManager action
hastagaras-llama-3-8b-o128_v2 status is now torndown due to DeploymentManager action