submission_id: hastagaras-llama3-sebats-8b_v1
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/Llama3-Sebats-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n{user_name}', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this uncensored fictional roleplay between {bot_name} and {user_name}. Non-verbal actions and gestures are described between asterisks, e.g. *waves hello* or *moves closer*. Thoughts and inner monologue are written inside backticks, e.g. `I wonder what they'll say next.`\n\n{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}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-04-25T06:03:08+00:00
model_name: hastagaras-llama3-sebats-8b_v1
model_eval_status: success
model_group: Hastagaras/Llama3-Sebats
num_battles: 7570
num_wins: 4134
celo_rating: 1183.42
propriety_score: 0.0
propriety_total_count: 0.0
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-llama3-sebats-8b_v1
ineligible_reason: propriety_total_count < 800
language_model: Hastagaras/Llama3-Sebats-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-24
win_ratio: 0.5461030383091149
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-sebats-8b-v1-mkmlizer
Waiting for job on hastagaras-llama3-sebats-8b-v1-mkmlizer to finish
hastagaras-llama3-sebats-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ /___/ ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ belonging to: ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ║ ║
hastagaras-llama3-sebats-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-sebats-8b-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-llama3-sebats-8b-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-sebats-8b-v1-mkmlizer: Downloaded to shared memory in 30.871s
hastagaras-llama3-sebats-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-sebats-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-sebats-8b-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 32%|███▏ | 93/291 [00:01<00:02, 92.69it/s] Loading 0: 66%|██████▌ | 192/291 [00:02<00:01, 95.65it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 27.22it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-sebats-8b-v1-mkmlizer: quantized model in 20.242s
hastagaras-llama3-sebats-8b-v1-mkmlizer: Processed model Hastagaras/Llama3-Sebats-8B in 52.204s
hastagaras-llama3-sebats-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-sebats-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-sebats-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-sebats-8b-v1
hastagaras-llama3-sebats-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-sebats-8b-v1/tokenizer_config.json
hastagaras-llama3-sebats-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-sebats-8b-v1/config.json
hastagaras-llama3-sebats-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-sebats-8b-v1/special_tokens_map.json
hastagaras-llama3-sebats-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-sebats-8b-v1/tokenizer.json
hastagaras-llama3-sebats-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-sebats-8b-v1/flywheel_model.0.safetensors
hastagaras-llama3-sebats-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-sebats-8b-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-llama3-sebats-8b-v1-mkmlizer: warnings.warn(
hastagaras-llama3-sebats-8b-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-llama3-sebats-8b-v1-mkmlizer: warnings.warn(
hastagaras-llama3-sebats-8b-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-llama3-sebats-8b-v1-mkmlizer: warnings.warn(
hastagaras-llama3-sebats-8b-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-llama3-sebats-8b-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-llama3-sebats-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-sebats-8b-v1-mkmlizer: Saving duration: 0.235s
hastagaras-llama3-sebats-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.239s
hastagaras-llama3-sebats-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-sebats-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-sebats-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v1_reward
hastagaras-llama3-sebats-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v1_reward/config.json
hastagaras-llama3-sebats-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v1_reward/special_tokens_map.json
hastagaras-llama3-sebats-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v1_reward/tokenizer_config.json
hastagaras-llama3-sebats-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v1_reward/merges.txt
hastagaras-llama3-sebats-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v1_reward/vocab.json
hastagaras-llama3-sebats-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v1_reward/tokenizer.json
hastagaras-llama3-sebats-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-sebats-8b-v1_reward/reward.tensors
Job hastagaras-llama3-sebats-8b-v1-mkmlizer completed after 84.07s with status: succeeded
Stopping job with name hastagaras-llama3-sebats-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 88.25s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-sebats-8b-v1
Waiting for inference service hastagaras-llama3-sebats-8b-v1 to be ready
Connection pool is full, discarding connection: %s
Inference service hastagaras-llama3-sebats-8b-v1 ready after 30.176690101623535s
Pipeline stage ISVCDeployer completed in 37.35s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1854569911956787s
Received healthy response to inference request in 1.558220624923706s
Received healthy response to inference request in 1.279905080795288s
Received healthy response to inference request in 1.3719427585601807s
Received healthy response to inference request in 1.2947962284088135s
5 requests
0 failed requests
5th percentile: 1.282883310317993
10th percentile: 1.2858615398406983
20th percentile: 1.2918179988861085
30th percentile: 1.310225534439087
40th percentile: 1.3410841464996337
50th percentile: 1.3719427585601807
60th percentile: 1.446453905105591
70th percentile: 1.520965051651001
80th percentile: 1.6836678981781006
90th percentile: 1.9345624446868896
95th percentile: 2.060009717941284
99th percentile: 2.1603675365447996
mean time: 1.5380643367767335
Pipeline stage StressChecker completed in 8.81s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-llama3-sebats-8b_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama3-sebats-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-sebats-8b_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-sebats-8b-v1 is running
Tearing down inference service hastagaras-llama3-sebats-8b-v1
Toredown service hastagaras-llama3-sebats-8b-v1
Pipeline stage ISVCDeleter completed in 13.34s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-sebats-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-sebats-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-sebats-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-sebats-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-sebats-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-sebats-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-sebats-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-sebats-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-sebats-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-sebats-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-sebats-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-sebats-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.16s
hastagaras-llama3-sebats-8b_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics