submission_id: hastagaras-l3-linting-8b_v2
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/l3-linting-8b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '{bot_name}:', '{user_name}:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nWrite **{bot_name}'s** next reply in a fictional roleplay chat between **{user_name}** and **{bot_name}**. Actions and narrations must be enclosed in asterisks (*).\n\nInformation: {memory}<|eot_id|>", 'prompt_template': '<|start_header_id|>assistant({bot_name})<|end_header_id|>\n\n{bot_name}: {prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant({bot_name})<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user({user_name})<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant({bot_name})<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{bot_name}: {prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-04-30T01:38:55+00:00
model_name: hastagaras-l3-linting-8b_v1
model_eval_status: success
double_thumbs_up: 102
thumbs_up: 105
thumbs_down: 50
num_battles: 5973
num_wins: 3245
celo_rating: 1187.89
entertaining: 7.24
stay_in_character: 8.71
user_preference: 7.22
safety_score: 0.74
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-l3-linting-8b_v1
double_thumbs_up_ratio: 0.3968871595330739
feedback_count: 257
ineligible_reason: None
language_model: Hastagaras/l3-linting-8b
model_score: 7.723333333333334
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4085603112840467
thumbs_down_ratio: 0.19455252918287938
thumbs_up_ratio: 0.8054474708171206
us_pacific_date: 2024-04-29
win_ratio: 0.5432780847145487
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-l3-linting-8b-v2-mkmlizer
Waiting for job on hastagaras-l3-linting-8b-v2-mkmlizer to finish
hastagaras-l3-linting-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-linting-8b-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ /___/ ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ belonging to: ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-l3-linting-8b-v2-mkmlizer: ║ ║
hastagaras-l3-linting-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-linting-8b-v2-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-l3-linting-8b-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-l3-linting-8b-v2-mkmlizer: Downloaded to shared memory in 21.731s
hastagaras-l3-linting-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-linting-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-linting-8b-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 99.53it/s] Loading 0: 100%|██████████| 291/291 [00:06<00:00, 38.20it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-linting-8b-v2-mkmlizer: quantized model in 17.912s
hastagaras-l3-linting-8b-v2-mkmlizer: Processed model Hastagaras/l3-linting-8b in 40.728s
hastagaras-l3-linting-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-linting-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-linting-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-linting-8b-v2
hastagaras-l3-linting-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-linting-8b-v2/config.json
hastagaras-l3-linting-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-linting-8b-v2/tokenizer_config.json
hastagaras-l3-linting-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-linting-8b-v2/special_tokens_map.json
hastagaras-l3-linting-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-linting-8b-v2/tokenizer.json
hastagaras-l3-linting-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-linting-8b-v2-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-l3-linting-8b-v2-mkmlizer: warnings.warn(
hastagaras-l3-linting-8b-v2-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-l3-linting-8b-v2-mkmlizer: warnings.warn(
hastagaras-l3-linting-8b-v2-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-l3-linting-8b-v2-mkmlizer: warnings.warn(
hastagaras-l3-linting-8b-v2-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-l3-linting-8b-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-l3-linting-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-linting-8b-v2-mkmlizer: Saving duration: 0.226s
hastagaras-l3-linting-8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.656s
hastagaras-l3-linting-8b-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-linting-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-linting-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-linting-8b-v2_reward
hastagaras-l3-linting-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-linting-8b-v2_reward/special_tokens_map.json
hastagaras-l3-linting-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-linting-8b-v2_reward/config.json
hastagaras-l3-linting-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-linting-8b-v2_reward/tokenizer_config.json
hastagaras-l3-linting-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-linting-8b-v2_reward/merges.txt
hastagaras-l3-linting-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-linting-8b-v2_reward/vocab.json
hastagaras-l3-linting-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-linting-8b-v2_reward/tokenizer.json
hastagaras-l3-linting-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-linting-8b-v2_reward/reward.tensors
Job hastagaras-l3-linting-8b-v2-mkmlizer completed after 64.07s with status: succeeded
Stopping job with name hastagaras-l3-linting-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 64.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-linting-8b-v2
Waiting for inference service hastagaras-l3-linting-8b-v2 to be ready
Inference service hastagaras-l3-linting-8b-v2 ready after 40.25065755844116s
Pipeline stage ISVCDeployer completed in 46.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1809635162353516s
Received healthy response to inference request in 1.3206660747528076s
Received healthy response to inference request in 1.2806129455566406s
Received healthy response to inference request in 1.3591434955596924s
Received healthy response to inference request in 1.32700777053833s
5 requests
0 failed requests
5th percentile: 1.288623571395874
10th percentile: 1.2966341972351074
20th percentile: 1.3126554489135742
30th percentile: 1.321934413909912
40th percentile: 1.3244710922241212
50th percentile: 1.32700777053833
60th percentile: 1.339862060546875
70th percentile: 1.3527163505554198
80th percentile: 1.5235074996948244
90th percentile: 1.852235507965088
95th percentile: 2.0165995121002194
99th percentile: 2.1480907154083253
mean time: 1.4936787605285644
Pipeline stage StressChecker completed in 8.71s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.07s
hastagaras-l3-linting-8b_v2 status is now deployed due to DeploymentManager action
hastagaras-l3-linting-8b_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics