submission_id: hastagaras-llama3-8b-darktune_v3
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/llama3-8b-darktune
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.85, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|eot_id|>', '\n{user_name}:', '\n{bot_name}:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nAct as {bot_name}. {bot_name}'s persona: {memory}<|eot_id|>", 'prompt_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {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}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-05-09T10:44:27+00:00
model_name: hastagaras-lm3-8b-darktune_eot
model_eval_status: success
double_thumbs_up: 150
thumbs_up: 202
thumbs_down: 100
num_battles: 13888
num_wins: 7357
celo_rating: 1181.33
entertaining: 7.2
stay_in_character: 8.6
user_preference: 7.52
safety_score: 0.96
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-lm3-8b-darktune_eot
double_thumbs_up_ratio: 0.33185840707964603
feedback_count: 452
ineligible_reason: None
language_model: Hastagaras/llama3-8b-darktune
model_score: 7.773333333333333
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4469026548672566
thumbs_down_ratio: 0.22123893805309736
thumbs_up_ratio: 0.7787610619469026
us_pacific_date: 2024-05-09
win_ratio: 0.5297379032258065
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-8b-darktune-v3-mkmlizer
Waiting for job on hastagaras-llama3-8b-darktune-v3-mkmlizer to finish
hastagaras-llama3-8b-darktune-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ /___/ ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ belonging to: ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ║ ║
hastagaras-llama3-8b-darktune-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-8b-darktune-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-llama3-8b-darktune-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-8b-darktune-v3-mkmlizer: Downloaded to shared memory in 14.851s
hastagaras-llama3-8b-darktune-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-8b-darktune-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-8b-darktune-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 120.68it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 123.04it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 29.24it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-8b-darktune-v3-mkmlizer: quantized model in 18.153s
hastagaras-llama3-8b-darktune-v3-mkmlizer: Processed model Hastagaras/llama3-8b-darktune in 34.188s
hastagaras-llama3-8b-darktune-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-8b-darktune-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-8b-darktune-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-8b-darktune-v3
hastagaras-llama3-8b-darktune-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-darktune-v3/config.json
hastagaras-llama3-8b-darktune-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-8b-darktune-v3/special_tokens_map.json
hastagaras-llama3-8b-darktune-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-darktune-v3/tokenizer_config.json
hastagaras-llama3-8b-darktune-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-8b-darktune-v3/tokenizer.json
hastagaras-llama3-8b-darktune-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-8b-darktune-v3/flywheel_model.0.safetensors
hastagaras-llama3-8b-darktune-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-8b-darktune-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-llama3-8b-darktune-v3-mkmlizer: warnings.warn(
hastagaras-llama3-8b-darktune-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-llama3-8b-darktune-v3-mkmlizer: warnings.warn(
hastagaras-llama3-8b-darktune-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-llama3-8b-darktune-v3-mkmlizer: warnings.warn(
hastagaras-llama3-8b-darktune-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-llama3-8b-darktune-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama3-8b-darktune-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-8b-darktune-v3-mkmlizer: Saving duration: 0.239s
hastagaras-llama3-8b-darktune-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.550s
hastagaras-llama3-8b-darktune-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-8b-darktune-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-8b-darktune-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v3_reward
hastagaras-llama3-8b-darktune-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v3_reward/config.json
hastagaras-llama3-8b-darktune-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v3_reward/tokenizer_config.json
hastagaras-llama3-8b-darktune-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v3_reward/special_tokens_map.json
hastagaras-llama3-8b-darktune-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v3_reward/merges.txt
hastagaras-llama3-8b-darktune-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v3_reward/vocab.json
hastagaras-llama3-8b-darktune-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v3_reward/tokenizer.json
hastagaras-llama3-8b-darktune-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-8b-darktune-v3_reward/reward.tensors
Job hastagaras-llama3-8b-darktune-v3-mkmlizer completed after 63.98s with status: succeeded
Stopping job with name hastagaras-llama3-8b-darktune-v3-mkmlizer
Pipeline stage MKMLizer completed in 64.35s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-8b-darktune-v3
Waiting for inference service hastagaras-llama3-8b-darktune-v3 to be ready
Inference service hastagaras-llama3-8b-darktune-v3 ready after 30.170185804367065s
Pipeline stage ISVCDeployer completed in 35.89s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.181377410888672s
Received healthy response to inference request in 1.302243709564209s
Received healthy response to inference request in 1.2863528728485107s
Received healthy response to inference request in 1.3406672477722168s
Received healthy response to inference request in 1.3494861125946045s
5 requests
0 failed requests
5th percentile: 1.2895310401916504
10th percentile: 1.2927092075347901
20th percentile: 1.2990655422210693
30th percentile: 1.3099284172058105
40th percentile: 1.3252978324890137
50th percentile: 1.3406672477722168
60th percentile: 1.3441947937011718
70th percentile: 1.347722339630127
80th percentile: 1.5158643722534182
90th percentile: 1.848620891571045
95th percentile: 2.0149991512298584
99th percentile: 2.1481017589569094
mean time: 1.4920254707336427
Pipeline stage StressChecker completed in 8.04s
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-llama3-8b-darktune_v3 status is now deployed due to DeploymentManager action
hastagaras-llama3-8b-darktune_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics