submission_id: hastagaras-wadidaw-8b-llama3_v1
developer_uid: Hastagaras
best_of: 16
celo_rating: 1206.74
display_name: hopefully-works
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': 0.95, '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/Wadidaw-8B-Llama3
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/Wadidaw-8B-Ll
model_name: hopefully-works
model_num_parameters: 8030261248.0
model_repo: Hastagaras/Wadidaw-8B-Llama3
model_size: 8B
num_battles: 6547
num_wins: 3530
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: 2024-06-01T10:31:03+00:00
us_pacific_date: 2024-06-01
win_ratio: 0.5391782495799603
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-wadidaw-8b-llama3-v1-mkmlizer
Waiting for job on hastagaras-wadidaw-8b-llama3-v1-mkmlizer to finish
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ /___/ ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ belonging to: ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ║ ║
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-wadidaw-8b-llama3-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-wadidaw-8b-llama3-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: Downloaded to shared memory in 29.695s
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 132.67it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 149.66it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 153.64it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 157.39it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 80.09it/s] Loading 0: 33%|███▎ | 96/291 [00:00<00:02, 82.63it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:01, 91.31it/s] Loading 0: 42%|████▏ | 123/291 [00:01<00:01, 94.62it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 109.71it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 124.31it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 144.52it/s] Loading 0: 67%|██████▋ | 195/291 [00:01<00:01, 87.03it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:00, 100.62it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 114.35it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 125.43it/s] Loading 0: 90%|█████████ | 262/291 [00:02<00:00, 130.06it/s] Loading 0: 95%|█████████▌| 277/291 [00:02<00:00, 122.24it/s] Loading 0: 100%|██████████| 291/291 [00:08<00:00, 8.69it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: quantized model in 23.379s
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: Processed model Hastagaras/Wadidaw-8B-Llama3 in 55.666s
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-wadidaw-8b-llama3-v1
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-wadidaw-8b-llama3-v1/tokenizer_config.json
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-wadidaw-8b-llama3-v1/config.json
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-wadidaw-8b-llama3-v1/special_tokens_map.json
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-wadidaw-8b-llama3-v1/tokenizer.json
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-wadidaw-8b-llama3-v1/flywheel_model.0.safetensors
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-wadidaw-8b-llama3-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-wadidaw-8b-llama3-v1-mkmlizer: warnings.warn(
hastagaras-wadidaw-8b-llama3-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-wadidaw-8b-llama3-v1-mkmlizer: warnings.warn(
hastagaras-wadidaw-8b-llama3-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-wadidaw-8b-llama3-v1-mkmlizer: warnings.warn(
hastagaras-wadidaw-8b-llama3-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-wadidaw-8b-llama3-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: Saving duration: 0.429s
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.469s
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-wadidaw-8b-llama3-v1_reward
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-wadidaw-8b-llama3-v1_reward/config.json
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-wadidaw-8b-llama3-v1_reward/tokenizer_config.json
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-wadidaw-8b-llama3-v1_reward/special_tokens_map.json
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-wadidaw-8b-llama3-v1_reward/merges.txt
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-wadidaw-8b-llama3-v1_reward/vocab.json
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-wadidaw-8b-llama3-v1_reward/tokenizer.json
hastagaras-wadidaw-8b-llama3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-wadidaw-8b-llama3-v1_reward/reward.tensors
Job hastagaras-wadidaw-8b-llama3-v1-mkmlizer completed after 83.16s with status: succeeded
Stopping job with name hastagaras-wadidaw-8b-llama3-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.27s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-wadidaw-8b-llama3-v1
Waiting for inference service hastagaras-wadidaw-8b-llama3-v1 to be ready
Inference service hastagaras-wadidaw-8b-llama3-v1 ready after 200.91375923156738s
Pipeline stage ISVCDeployer completed in 208.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.158055305480957s
Received healthy response to inference request in 1.3081727027893066s
Received healthy response to inference request in 1.3266575336456299s
Received healthy response to inference request in 1.2802114486694336s
Received healthy response to inference request in 1.231335163116455s
5 requests
0 failed requests
5th percentile: 1.2411104202270509
10th percentile: 1.2508856773376464
20th percentile: 1.2704361915588378
30th percentile: 1.2858036994934081
40th percentile: 1.2969882011413574
50th percentile: 1.3081727027893066
60th percentile: 1.315566635131836
70th percentile: 1.3229605674743652
80th percentile: 1.4929370880126955
90th percentile: 1.8254961967468262
95th percentile: 1.9917757511138914
99th percentile: 2.124799394607544
mean time: 1.4608864307403564
Pipeline stage StressChecker completed in 7.96s
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-wadidaw-8b-llama3_v1 status is now deployed due to DeploymentManager action
hastagaras-wadidaw-8b-llama3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-wadidaw-8b-llama3_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-wadidaw-8b-llama3-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.25s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-wadidaw-8b-llama3-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-wadidaw-8b-llama3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-wadidaw-8b-llama3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-wadidaw-8b-llama3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-wadidaw-8b-llama3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-wadidaw-8b-llama3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-wadidaw-8b-llama3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-wadidaw-8b-llama3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-wadidaw-8b-llama3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-wadidaw-8b-llama3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-wadidaw-8b-llama3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-wadidaw-8b-llama3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.17s
hastagaras-wadidaw-8b-llama3_v1 status is now torndown due to DeploymentManager action