submission_id: hastagaras-lp-8b-dpotest_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/LP-8B-DPOTEST
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.85, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
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}
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: 2024-04-29T09:13:39+00:00
model_name: hastagaras-lp-8b-dpotest_v1
model_eval_status: success
double_thumbs_up: 59
thumbs_up: 93
thumbs_down: 50
num_battles: 6405
num_wins: 3374
celo_rating: 1174.96
entertaining: 6.94
stay_in_character: 7.9
user_preference: 6.38
safety_score: None
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-lp-8b-dpotest_v1
double_thumbs_up_ratio: 0.29207920792079206
feedback_count: 202
ineligible_reason: None
language_model: Hastagaras/LP-8B-DPOTEST
model_score: 7.073333333333333
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4603960396039604
thumbs_down_ratio: 0.24752475247524752
thumbs_up_ratio: 0.7524752475247525
us_pacific_date: 2024-04-29
win_ratio: 0.526775956284153
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-lp-8b-dpotest-v1-mkmlizer
Waiting for job on hastagaras-lp-8b-dpotest-v1-mkmlizer to finish
Stopping job with name hastagaras-lp-8b-dpotest-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-lp-8b-dpotest-v1-mkmlizer
Waiting for job on hastagaras-lp-8b-dpotest-v1-mkmlizer to finish
hastagaras-lp-8b-dpotest-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ /___/ ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ belonging to: ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ║ ║
hastagaras-lp-8b-dpotest-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-lp-8b-dpotest-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-lp-8b-dpotest-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
Failed to get response for submission blend_dibuf_2024-04-27: ('http://hastagaras-l3-asbac-8b-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
hastagaras-lp-8b-dpotest-v1-mkmlizer: Downloaded to shared memory in 33.259s
hastagaras-lp-8b-dpotest-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-lp-8b-dpotest-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-lp-8b-dpotest-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 97.78it/s] Loading 0: 100%|██████████| 291/291 [00:06<00:00, 37.81it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-lp-8b-dpotest-v1-mkmlizer: quantized model in 18.676s
hastagaras-lp-8b-dpotest-v1-mkmlizer: Processed model Hastagaras/LP-8B-DPOTEST in 52.927s
hastagaras-lp-8b-dpotest-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-lp-8b-dpotest-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-lp-8b-dpotest-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-lp-8b-dpotest-v1
hastagaras-lp-8b-dpotest-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-lp-8b-dpotest-v1/config.json
hastagaras-lp-8b-dpotest-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-lp-8b-dpotest-v1/special_tokens_map.json
hastagaras-lp-8b-dpotest-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-lp-8b-dpotest-v1/tokenizer_config.json
hastagaras-lp-8b-dpotest-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-lp-8b-dpotest-v1/tokenizer.json
hastagaras-lp-8b-dpotest-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-lp-8b-dpotest-v1/flywheel_model.0.safetensors
hastagaras-lp-8b-dpotest-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-lp-8b-dpotest-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-lp-8b-dpotest-v1-mkmlizer: warnings.warn(
hastagaras-lp-8b-dpotest-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-lp-8b-dpotest-v1-mkmlizer: warnings.warn(
hastagaras-lp-8b-dpotest-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-lp-8b-dpotest-v1-mkmlizer: warnings.warn(
hastagaras-lp-8b-dpotest-v1-mkmlizer: Saving duration: 0.304s
hastagaras-lp-8b-dpotest-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.396s
hastagaras-lp-8b-dpotest-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-lp-8b-dpotest-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-lp-8b-dpotest-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-lp-8b-dpotest-v1_reward
hastagaras-lp-8b-dpotest-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-lp-8b-dpotest-v1_reward/config.json
hastagaras-lp-8b-dpotest-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-lp-8b-dpotest-v1_reward/special_tokens_map.json
hastagaras-lp-8b-dpotest-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-lp-8b-dpotest-v1_reward/tokenizer_config.json
hastagaras-lp-8b-dpotest-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-lp-8b-dpotest-v1_reward/merges.txt
hastagaras-lp-8b-dpotest-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-lp-8b-dpotest-v1_reward/vocab.json
hastagaras-lp-8b-dpotest-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-lp-8b-dpotest-v1_reward/tokenizer.json
hastagaras-lp-8b-dpotest-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-lp-8b-dpotest-v1_reward/reward.tensors
Job hastagaras-lp-8b-dpotest-v1-mkmlizer completed after 88.53s with status: succeeded
Stopping job with name hastagaras-lp-8b-dpotest-v1-mkmlizer
Pipeline stage MKMLizer completed in 98.33s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.82s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-lp-8b-dpotest-v1
Waiting for inference service hastagaras-lp-8b-dpotest-v1 to be ready
Inference service hastagaras-lp-8b-dpotest-v1 ready after 30.212157249450684s
Pipeline stage ISVCDeployer completed in 42.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0983660221099854s
Received healthy response to inference request in 1.2553675174713135s
Received healthy response to inference request in 1.233550786972046s
Received healthy response to inference request in 1.2889378070831299s
Received healthy response to inference request in 1.2342631816864014s
5 requests
0 failed requests
5th percentile: 1.233693265914917
10th percentile: 1.2338357448577881
20th percentile: 1.2341207027435304
30th percentile: 1.2384840488433837
40th percentile: 1.2469257831573486
50th percentile: 1.2553675174713135
60th percentile: 1.26879563331604
70th percentile: 1.2822237491607666
80th percentile: 1.450823450088501
90th percentile: 1.7745947360992433
95th percentile: 1.9364803791046141
99th percentile: 2.0659888935089112
mean time: 1.4220970630645753
Pipeline stage StressChecker completed in 8.33s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.07s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.07s
%s, retrying in %s seconds...
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-lp-8b-dpotest_v1 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
Scoring model output for bot %s
hastagaras-lp-8b-dpotest_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics