hastagaras-halu-8b-llama_9226

submission_id: hastagaras-halu-8b-llama_9226_v2

developer_uid: Hastagaras

best_of: 16

celo_rating: 1220.47

display_name: experiment-2-high-temp-test

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': 1.1, '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}

is_internal_developer: False

language_model: Hastagaras/HALU-8B-LLAMA3-EXP-2

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: Hastagaras/HALU-8B-LLAMA

model_name: experiment-2-high-temp-test

model_num_parameters: 8030261248.0

model_repo: Hastagaras/HALU-8B-LLAMA3-EXP-2

model_size: 8B

num_battles: 11439

num_wins: 6169

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: 2024-05-31T12:12:43+00:00

us_pacific_date: 2024-05-31

win_ratio: 0.5392953929539296

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-9226-v2-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-9226-v2-mkmlizer to finish
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-9226-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-9226-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-halu-8b-llama-9226-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-9226-v2-mkmlizer: Downloaded to shared memory in 20.511s
hastagaras-halu-8b-llama-9226-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-9226-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-9226-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:40,  2.22s/it]
Loading 0:   6%|▌         | 18/291 [00:04<00:50,  5.43it/s]
Loading 0:  12%|█▏        | 35/291 [00:04<00:20, 12.45it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 20.90it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.72it/s]
Loading 0:  28%|██▊       | 82/291 [00:05<00:05, 37.89it/s]
Loading 0:  34%|███▍      | 99/291 [00:05<00:03, 52.14it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 65.18it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 82.60it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 99.82it/s]
Loading 0:  57%|█████▋    | 166/291 [00:05<00:01, 71.42it/s]
Loading 0:  62%|██████▏   | 179/291 [00:06<00:01, 75.93it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:01, 90.50it/s]
Loading 0:  73%|███████▎  | 213/291 [00:06<00:00, 106.72it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:00, 121.69it/s]
Loading 0:  86%|████████▌ | 249/291 [00:06<00:00, 133.95it/s]
Loading 0:  91%|█████████▏| 266/291 [00:06<00:00, 89.73it/s] 
Loading 0:  96%|█████████▌| 280/291 [00:06<00:00, 98.76it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-9226-v2-mkmlizer: quantized model in 22.564s
hastagaras-halu-8b-llama-9226-v2-mkmlizer: Processed model Hastagaras/HALU-8B-LLAMA3-EXP-2 in 45.550s
hastagaras-halu-8b-llama-9226-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-9226-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-9226-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-9226-v2
hastagaras-halu-8b-llama-9226-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-9226-v2/config.json
hastagaras-halu-8b-llama-9226-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-9226-v2/special_tokens_map.json
hastagaras-halu-8b-llama-9226-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-9226-v2/tokenizer_config.json
hastagaras-halu-8b-llama-9226-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-9226-v2/tokenizer.json
hastagaras-halu-8b-llama-9226-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-9226-v2/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-9226-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-9226-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-halu-8b-llama-9226-v2-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-9226-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-halu-8b-llama-9226-v2-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-9226-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-halu-8b-llama-9226-v2-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-9226-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-halu-8b-llama-9226-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-9226-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-9226-v2-mkmlizer: Saving duration: 0.398s
hastagaras-halu-8b-llama-9226-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.241s
hastagaras-halu-8b-llama-9226-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-9226-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-9226-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v2_reward
hastagaras-halu-8b-llama-9226-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v2_reward/config.json
hastagaras-halu-8b-llama-9226-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v2_reward/tokenizer_config.json
hastagaras-halu-8b-llama-9226-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v2_reward/special_tokens_map.json
hastagaras-halu-8b-llama-9226-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v2_reward/merges.txt
hastagaras-halu-8b-llama-9226-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v2_reward/vocab.json
hastagaras-halu-8b-llama-9226-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v2_reward/tokenizer.json
hastagaras-halu-8b-llama-9226-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-9226-v2_reward/reward.tensors
Job hastagaras-halu-8b-llama-9226-v2-mkmlizer completed after 73.21s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-9226-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.58s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-9226-v2
Waiting for inference service hastagaras-halu-8b-llama-9226-v2 to be ready
Inference service hastagaras-halu-8b-llama-9226-v2 ready after 40.219019651412964s
Pipeline stage ISVCDeployer completed in 45.75s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.192025661468506s
Received healthy response to inference request in 1.319448471069336s
Received healthy response to inference request in 1.3033010959625244s
Received healthy response to inference request in 1.300574779510498s
Received healthy response to inference request in 1.2678248882293701s
5 requests
0 failed requests
5th percentile: 1.2743748664855956
10th percentile: 1.2809248447418213
20th percentile: 1.2940248012542725
30th percentile: 1.3011200428009033
40th percentile: 1.3022105693817139
50th percentile: 1.3033010959625244
60th percentile: 1.309760046005249
70th percentile: 1.3162189960479735
80th percentile: 1.49396390914917
90th percentile: 1.842994785308838
95th percentile: 2.0175102233886717
99th percentile: 2.157122573852539
mean time: 1.4766349792480469
Pipeline stage StressChecker completed in 8.02s
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 0.07s
hastagaras-halu-8b-llama_9226_v2 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_9226_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llama_9226_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llama-9226-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.70s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-9226-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-9226-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-9226-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-9226-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-9226-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-9226-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-9226-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-9226-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-9226-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-9226-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-9226-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-9226-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.82s
hastagaras-halu-8b-llama_9226_v2 status is now torndown due to DeploymentManager action