submission_id: cgato-l3-thespice-8b-dpo_5273_v2
developer_uid: c.gato
status: torndown
model_repo: cgato/L3-TheSpice-8b-DPO-v2.3-e1.2
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'], '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: 2024-04-30T18:56:29+00:00
model_name: cgato-l3-thespice-8b-dpo_5273_v2
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 8244
num_wins: 4638
celo_rating: 1200.52
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: cgato-l3-thespice-8b-dpo_5273_v2
ineligible_reason: propriety_total_count < 800
language_model: cgato/L3-TheSpice-8b-DPO-v2.3-e1.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-30
win_ratio: 0.5625909752547307
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer to finish
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-5273-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.
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 97.37it/s] Loading 0: 100%|██████████| 291/291 [00:06<00:00, 38.18it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: quantized model in 18.567s
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v2.3-e1.2 in 125.282s
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5273-v2
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5273-v2/special_tokens_map.json
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5273-v2/config.json
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5273-v2/tokenizer_config.json
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5273-v2/tokenizer.json
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5273-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-5273-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.
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5273-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.
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5273-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.
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5273-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()
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: Saving duration: 0.303s
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 29.619s
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5273-v2_reward
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5273-v2_reward/config.json
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5273-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5273-v2_reward/vocab.json
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5273-v2_reward/merges.txt
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5273-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5273-v2_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5273-v2_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer completed after 221.44s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-5273-v2-mkmlizer
Pipeline stage MKMLizer completed in 224.40s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-5273-v2
Waiting for inference service cgato-l3-thespice-8b-dpo-5273-v2 to be ready
Inference service cgato-l3-thespice-8b-dpo-5273-v2 ready after 40.24020552635193s
Pipeline stage ISVCDeployer completed in 48.55s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.135995864868164s
Received healthy response to inference request in 1.2803771495819092s
Received healthy response to inference request in 1.3031408786773682s
Received healthy response to inference request in 1.2886226177215576s
Received healthy response to inference request in 1.2819263935089111s
5 requests
0 failed requests
5th percentile: 1.2806869983673095
10th percentile: 1.28099684715271
20th percentile: 1.2816165447235108
30th percentile: 1.2832656383514405
40th percentile: 1.285944128036499
50th percentile: 1.2886226177215576
60th percentile: 1.2944299221038817
70th percentile: 1.300237226486206
80th percentile: 1.4697118759155274
90th percentile: 1.8028538703918457
95th percentile: 1.9694248676300048
99th percentile: 2.102681665420532
mean time: 1.458012580871582
Pipeline stage StressChecker completed in 8.06s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.06s
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 0.16s
cgato-l3-thespice-8b-dpo_5273_v2 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_5273_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-dpo_5273_v2
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-dpo-5273-v2 is running
Tearing down inference service cgato-l3-thespice-8b-dpo-5273-v2
Toredown service cgato-l3-thespice-8b-dpo-5273-v2
Pipeline stage ISVCDeleter completed in 4.56s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-5273-v2/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-5273-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-5273-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-5273-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-5273-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-5273-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-5273-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-5273-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-5273-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-5273-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-5273-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-5273-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.03s
cgato-l3-thespice-8b-dpo_5273_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics