submission_id: cgato-l3-thespice-8b-v0-1-3_v8
developer_uid: c.gato
best_of: 16
celo_rating: 1145.96
display_name: cgato-l3-thespice-8b-v0-1-3_v7
family_friendly_score: 0.0
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n {bot_name} responds in one line.\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}
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 70, 'presence_penalty': 0.9, 'frequency_penalty': 0.9, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 112}
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: cgato/L3-TheSpice-8b-v0.1.3
max_input_tokens: 512
max_output_tokens: 112
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-v0.
model_name: cgato-l3-thespice-8b-v0-1-3_v7
model_num_parameters: 8030261248.0
model_repo: cgato/L3-TheSpice-8b-v0.1.3
model_size: 8B
num_battles: 7159
num_wins: 3540
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n {bot_name} gives single line responses.\n{bot_name} gives short responses.\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: 2024-04-21T12:58:35+00:00
us_pacific_date: 2024-04-21
win_ratio: 0.4944824696186618
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer to finish
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-v0-1-3-v8-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.
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: Downloaded to shared memory in 24.484s
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 80.20it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 85.13it/s] Loading 0: 99%|█████████▊| 287/291 [00:09<00:00, 25.80it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: quantized model in 21.363s
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: Processed model cgato/L3-TheSpice-8b-v0.1.3 in 47.034s
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-1-3-v8/tokenizer.json
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-1-3-v8/flywheel_model.0.safetensors
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-v0-1-3-v8-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.
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-1-3-v8-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.
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-1-3-v8-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.
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-1-3-v8-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()
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: Saving duration: 0.295s
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.374s
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v8_reward
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v8_reward/config.json
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v8_reward/special_tokens_map.json
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v8_reward/vocab.json
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v8_reward/tokenizer.json
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v8_reward/merges.txt
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v8_reward/tokenizer_config.json
cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-1-3-v8_reward/reward.tensors
Job cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer completed after 74.2s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-v0-1-3-v8-mkmlizer
Pipeline stage MKMLizer completed in 77.66s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-v0-1-3-v8
Waiting for inference service cgato-l3-thespice-8b-v0-1-3-v8 to be ready
Inference service cgato-l3-thespice-8b-v0-1-3-v8 ready after 40.36008810997009s
Pipeline stage ISVCDeployer completed in 50.82s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.90122652053833s
Received healthy response to inference request in 2.034996509552002s
Received healthy response to inference request in 2.0404088497161865s
Received healthy response to inference request in 2.0532753467559814s
Received healthy response to inference request in 2.0376057624816895s
5 requests
0 failed requests
5th percentile: 2.0355183601379396
10th percentile: 2.036040210723877
20th percentile: 2.0370839118957518
30th percentile: 2.038166379928589
40th percentile: 2.0392876148223875
50th percentile: 2.0404088497161865
60th percentile: 2.0455554485321046
70th percentile: 2.0507020473480226
80th percentile: 2.222865581512451
90th percentile: 2.5620460510253906
95th percentile: 2.7316362857818604
99th percentile: 2.867308473587036
mean time: 2.213502597808838
Pipeline stage StressChecker completed in 11.68s
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 0.06s
cgato-l3-thespice-8b-v0-1-3_v8 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-v0-1-3_v8 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-v0-1-3_v8
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-v0-1-3-v8 is running
Tearing down inference service cgato-l3-thespice-8b-v0-1-3-v8
Toredown service cgato-l3-thespice-8b-v0-1-3-v8
Pipeline stage ISVCDeleter completed in 4.78s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-1-3-v8/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v8/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v8/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v8/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v8/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-1-3-v8_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v8_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v8_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v8_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v8_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v8_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-1-3-v8_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.17s
cgato-l3-thespice-8b-v0-1-3_v8 status is now torndown due to DeploymentManager action