submission_id: hastagaras-halu-oas-8b-llama3_v3
developer_uid: Hastagaras
best_of: 16
celo_rating: 1205.96
display_name: high-temp
family_friendly_score: 0.0
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}
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.1, '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}
is_internal_developer: False
language_model: Hastagaras/Halu-OAS-8B-Llama3
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/Halu-OAS-8B-L
model_name: high-temp
model_num_parameters: 8030261248.0
model_repo: Hastagaras/Halu-OAS-8B-Llama3
model_size: 8B
num_battles: 13365
num_wins: 7349
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-27T12:51:59+00:00
us_pacific_date: 2024-05-27
win_ratio: 0.5498690609801721
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-oas-8b-llama3-v3-mkmlizer
Waiting for job on hastagaras-halu-oas-8b-llama3-v3-mkmlizer to finish
Stopping job with name hastagaras-halu-oas-8b-llama3-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-halu-oas-8b-llama3-v3-mkmlizer
Waiting for job on hastagaras-halu-oas-8b-llama3-v3-mkmlizer to finish
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ /___/ ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ belonging to: ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ║ ║
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-oas-8b-llama3-v3-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-halu-oas-8b-llama3-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: Downloaded to shared memory in 25.741s
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 107.18it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:02, 100.34it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 118.20it/s] Loading 0: 18%|█▊ | 51/291 [00:00<00:02, 109.39it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 117.31it/s] Loading 0: 27%|██▋ | 78/291 [00:00<00:01, 111.35it/s] Loading 0: 31%|███ | 90/291 [00:01<00:03, 58.64it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:02, 69.48it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:02, 75.12it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 90.19it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 91.71it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 105.79it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 104.64it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:01, 108.28it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 61.69it/s] Loading 0: 71%|███████ | 206/291 [00:02<00:01, 73.02it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 83.86it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 87.21it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 100.70it/s] Loading 0: 89%|████████▊ | 258/291 [00:02<00:00, 100.32it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 110.59it/s] Loading 0: 98%|█████████▊| 285/291 [00:03<00:00, 110.14it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: quantized model in 26.456s
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: Processed model Hastagaras/Halu-OAS-8B-Llama3 in 55.020s
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-oas-8b-llama3-v3
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-oas-8b-llama3-v3/config.json
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-oas-8b-llama3-v3/tokenizer.json
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-oas-8b-llama3-v3/flywheel_model.0.safetensors
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-oas-8b-llama3-v3-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-halu-oas-8b-llama3-v3-mkmlizer: warnings.warn(
hastagaras-halu-oas-8b-llama3-v3-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-halu-oas-8b-llama3-v3-mkmlizer: warnings.warn(
hastagaras-halu-oas-8b-llama3-v3-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-halu-oas-8b-llama3-v3-mkmlizer: warnings.warn(
hastagaras-halu-oas-8b-llama3-v3-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-halu-oas-8b-llama3-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: Saving duration: 0.526s
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.340s
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-oas-8b-llama3-v3_reward
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-llama3-v3_reward/special_tokens_map.json
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-llama3-v3_reward/config.json
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-llama3-v3_reward/tokenizer_config.json
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-oas-8b-llama3-v3_reward/merges.txt
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-llama3-v3_reward/vocab.json
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-llama3-v3_reward/tokenizer.json
hastagaras-halu-oas-8b-llama3-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-oas-8b-llama3-v3_reward/reward.tensors
Job hastagaras-halu-oas-8b-llama3-v3-mkmlizer completed after 84.26s with status: succeeded
Stopping job with name hastagaras-halu-oas-8b-llama3-v3-mkmlizer
Pipeline stage MKMLizer completed in 86.01s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-oas-8b-llama3-v3
Waiting for inference service hastagaras-halu-oas-8b-llama3-v3 to be ready
Inference service hastagaras-halu-oas-8b-llama3-v3 ready after 40.353108644485474s
Pipeline stage ISVCDeployer completed in 46.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1160528659820557s
Received healthy response to inference request in 1.3669703006744385s
Received healthy response to inference request in 1.3285551071166992s
Received healthy response to inference request in 1.3001551628112793s
Received healthy response to inference request in 1.2782247066497803s
5 requests
0 failed requests
5th percentile: 1.28261079788208
10th percentile: 1.28699688911438
20th percentile: 1.2957690715789796
30th percentile: 1.3058351516723632
40th percentile: 1.3171951293945312
50th percentile: 1.3285551071166992
60th percentile: 1.343921184539795
70th percentile: 1.3592872619628906
80th percentile: 1.5167868137359621
90th percentile: 1.8164198398590088
95th percentile: 1.966236352920532
99th percentile: 2.086089563369751
mean time: 1.4779916286468506
Pipeline stage StressChecker completed in 8.03s
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-halu-oas-8b-llama3_v3 status is now deployed due to DeploymentManager action
hastagaras-halu-oas-8b-llama3_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-oas-8b-llama3_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-oas-8b-llama3-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.31s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-oas-8b-llama3-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-oas-8b-llama3-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-oas-8b-llama3-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-oas-8b-llama3-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-oas-8b-llama3-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-oas-8b-llama3-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-oas-8b-llama3-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-oas-8b-llama3-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-oas-8b-llama3-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-oas-8b-llama3-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-oas-8b-llama3-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-oas-8b-llama3-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 4.01s
hastagaras-halu-oas-8b-llama3_v3 status is now torndown due to DeploymentManager action