submission_id: hastagaras-halu-8b-llama3-dt_v1
developer_uid: Hastagaras
best_of: 16
celo_rating: 1208.79
display_name: merge-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': 1.0, 'top_p': 0.95, 'min_p': 0.05, '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-DT
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
model_name: merge-test
model_num_parameters: 8030261248.0
model_repo: Hastagaras/Halu-8B-Llama3-DT
model_size: 8B
num_battles: 11474
num_wins: 6388
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: 2024-05-28T07:12:46+00:00
us_pacific_date: 2024-05-28
win_ratio: 0.5567369705420951
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama3-dt-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama3-dt-v1-mkmlizer to finish
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ /___/ ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ belonging to: ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ║ ║
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama3-dt-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-llama3-dt-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: Downloaded to shared memory in 46.794s
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:29, 2.38s/it] Loading 0: 5%|▍ | 14/291 [00:04<01:11, 3.88it/s] Loading 0: 10%|▉ | 28/291 [00:04<00:28, 9.28it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:15, 15.69it/s] Loading 0: 19%|█▉ | 55/291 [00:05<00:09, 24.44it/s] Loading 0: 23%|██▎ | 67/291 [00:05<00:08, 25.84it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.35it/s] Loading 0: 32%|███▏ | 94/291 [00:05<00:04, 47.74it/s] Loading 0: 36%|███▋ | 106/291 [00:05<00:03, 57.16it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 72.13it/s] Loading 0: 46%|████▌ | 134/291 [00:06<00:01, 81.45it/s] Loading 0: 51%|█████ | 148/291 [00:06<00:01, 93.39it/s] Loading 0: 55%|█████▌ | 161/291 [00:06<00:01, 98.77it/s] Loading 0: 60%|█████▉ | 174/291 [00:06<00:01, 69.78it/s] Loading 0: 64%|██████▎ | 185/291 [00:06<00:01, 75.86it/s] Loading 0: 68%|██████▊ | 199/291 [00:06<00:01, 88.43it/s] Loading 0: 73%|███████▎ | 212/291 [00:07<00:00, 95.74it/s] Loading 0: 77%|███████▋ | 225/291 [00:07<00:00, 103.85it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:00, 108.44it/s] Loading 0: 87%|████████▋ | 253/291 [00:07<00:00, 115.08it/s] Loading 0: 91%|█████████▏| 266/291 [00:07<00:00, 72.62it/s] Loading 0: 96%|█████████▌| 280/291 [00:07<00:00, 84.69it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: quantized model in 23.710s
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-DT in 72.990s
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-dt-v1
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-dt-v1/special_tokens_map.json
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-dt-v1/config.json
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-dt-v1/tokenizer_config.json
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-dt-v1/tokenizer.json
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama3-dt-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama3-dt-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-llama3-dt-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama3-dt-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-llama3-dt-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama3-dt-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-llama3-dt-v1-mkmlizer: warnings.warn(
hastagaras-halu-8b-llama3-dt-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-llama3-dt-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: Saving duration: 0.384s
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.604s
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama3-dt-v1_reward
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama3-dt-v1_reward/config.json
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama3-dt-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama3-dt-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama3-dt-v1_reward/merges.txt
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama3-dt-v1_reward/vocab.json
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama3-dt-v1_reward/tokenizer.json
hastagaras-halu-8b-llama3-dt-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama3-dt-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama3-dt-v1-mkmlizer completed after 113.64s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama3-dt-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.11s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama3-dt-v1
Waiting for inference service hastagaras-halu-8b-llama3-dt-v1 to be ready
Inference service hastagaras-halu-8b-llama3-dt-v1 ready after 90.42402052879333s
Pipeline stage ISVCDeployer completed in 97.49s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.193666696548462s
Received healthy response to inference request in 1.3444585800170898s
Received healthy response to inference request in 1.3345310688018799s
Received healthy response to inference request in 1.323547601699829s
Received healthy response to inference request in 1.2439000606536865s
5 requests
0 failed requests
5th percentile: 1.259829568862915
10th percentile: 1.2757590770721436
20th percentile: 1.3076180934906005
30th percentile: 1.3257442951202392
40th percentile: 1.3301376819610595
50th percentile: 1.3345310688018799
60th percentile: 1.3385020732879638
70th percentile: 1.342473077774048
80th percentile: 1.5143002033233643
90th percentile: 1.8539834499359131
95th percentile: 2.0238250732421874
99th percentile: 2.159698371887207
mean time: 1.4880208015441894
Pipeline stage StressChecker completed in 8.10s
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-8b-llama3-dt_v1 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama3-dt_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llama3-dt_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llama3-dt-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.20s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama3-dt-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama3-dt-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama3-dt-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama3-dt-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama3-dt-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama3-dt-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama3-dt-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama3-dt-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama3-dt-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama3-dt-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama3-dt-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama3-dt-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.85s
hastagaras-halu-8b-llama3-dt_v1 status is now torndown due to DeploymentManager action