hastagaras-halu-8b-llama_2887

submission_id: hastagaras-halu-8b-llama_2887_v1

developer_uid: Hastagaras

best_of: 16

celo_rating: 1214.46

display_name: 999

family_friendly_score: 0.0

formatter: {'memory_template': "<|begin_of_text|><|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': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 45, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

is_internal_developer: False

language_model: Hastagaras/Halu-8B-Llama3-v0.9-BR-TEST

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Hastagaras/Halu-8B-Llama

model_name: 999

model_num_parameters: 8030261248.0

model_repo: Hastagaras/Halu-8B-Llama3-v0.9-BR-TEST

model_size: 8B

num_battles: 28425

num_wins: 16102

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: 2024-06-22T02:06:03+00:00

us_pacific_date: 2024-06-21

win_ratio: 0.5664731750219877

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-2887-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-2887-v1-mkmlizer to finish
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-2887-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-2887-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-halu-8b-llama-2887-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-2887-v1-mkmlizer: Downloaded to shared memory in 30.111s
hastagaras-halu-8b-llama-2887-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-2887-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-2887-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:41,  2.22s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:01,  4.49it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:21, 11.95it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 21.50it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.72it/s]
Loading 0:  28%|██▊       | 81/291 [00:05<00:05, 36.86it/s]
Loading 0:  34%|███▎      | 98/291 [00:05<00:03, 50.98it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 64.95it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 82.10it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 98.42it/s]
Loading 0:  57%|█████▋    | 166/291 [00:05<00:01, 75.82it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 91.67it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 107.39it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 121.17it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 131.26it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 140.50it/s]
Loading 0:  93%|█████████▎| 272/291 [00:06<00:00, 89.54it/s] 
Loading 0:  99%|█████████▉| 288/291 [00:06<00:00, 101.91it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-2887-v1-mkmlizer: quantized model in 22.813s
hastagaras-halu-8b-llama-2887-v1-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.9-BR-TEST in 55.455s
hastagaras-halu-8b-llama-2887-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-2887-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-2887-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2887-v1
hastagaras-halu-8b-llama-2887-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2887-v1/config.json
hastagaras-halu-8b-llama-2887-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2887-v1/tokenizer_config.json
hastagaras-halu-8b-llama-2887-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2887-v1/tokenizer.json
hastagaras-halu-8b-llama-2887-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2887-v1/special_tokens_map.json
hastagaras-halu-8b-llama-2887-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2887-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-2887-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-2887-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-halu-8b-llama-2887-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-2887-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-halu-8b-llama-2887-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-2887-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-halu-8b-llama-2887-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-2887-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-halu-8b-llama-2887-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-2887-v1-mkmlizer: Saving duration: 0.433s
hastagaras-halu-8b-llama-2887-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.391s
hastagaras-halu-8b-llama-2887-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-2887-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-2887-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-2887-v1_reward
hastagaras-halu-8b-llama-2887-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2887-v1_reward/config.json
hastagaras-halu-8b-llama-2887-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2887-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama-2887-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2887-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama-2887-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-2887-v1_reward/merges.txt
hastagaras-halu-8b-llama-2887-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2887-v1_reward/vocab.json
hastagaras-halu-8b-llama-2887-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2887-v1_reward/tokenizer.json
hastagaras-halu-8b-llama-2887-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-2887-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama-2887-v1-mkmlizer completed after 83.92s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-2887-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.30s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-2887-v1
Waiting for inference service hastagaras-halu-8b-llama-2887-v1 to be ready
Inference service hastagaras-halu-8b-llama-2887-v1 ready after 40.17465543746948s
Pipeline stage ISVCDeployer completed in 45.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.196337938308716s
Received healthy response to inference request in 1.3480970859527588s
Received healthy response to inference request in 1.5379998683929443s
Received healthy response to inference request in 1.2784662246704102s
Received healthy response to inference request in 1.358750343322754s
5 requests
0 failed requests
5th percentile: 1.2923923969268798
10th percentile: 1.3063185691833497
20th percentile: 1.3341709136962892
30th percentile: 1.3502277374267577
40th percentile: 1.3544890403747558
50th percentile: 1.358750343322754
60th percentile: 1.43045015335083
70th percentile: 1.5021499633789062
80th percentile: 1.6696674823760986
90th percentile: 1.9330027103424072
95th percentile: 2.0646703243255615
99th percentile: 2.170004415512085
mean time: 1.5439302921295166
Pipeline stage StressChecker completed in 8.50s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
hastagaras-halu-8b-llama_2887_v1 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_2887_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llama_2887_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llama-2887-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.44s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-2887-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-2887-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-2887-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-2887-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-2887-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-2887-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-2887-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-2887-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-2887-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-2887-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-2887-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-2887-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.41s
hastagaras-halu-8b-llama_2887_v1 status is now torndown due to DeploymentManager action