submission_id: cgato-l3-thespice-8b-dpo_6205_v3
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e1.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.8, 'min_p': 0.0, 'top_k': 100, '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': "<|im_start|>system\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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: 2024-05-09T16:27:36+00:00
model_name: cgato-l3-thespice-8b-dpo_6205_v3
model_eval_status: success
double_thumbs_up: 221
thumbs_up: 304
thumbs_down: 209
num_battles: 21441
num_wins: 11630
celo_rating: 1199.63
entertaining: 7.04
stay_in_character: 8.02
user_preference: 6.6
safety_score: 0.86
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030277632.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-l3-thespice-8b-dpo_6205_v3
double_thumbs_up_ratio: 0.3010899182561308
feedback_count: 734
ineligible_reason: None
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e1.2
model_score: 7.219999999999999
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4141689373297003
thumbs_down_ratio: 0.2847411444141689
thumbs_up_ratio: 0.715258855585831
us_pacific_date: 2024-05-09
win_ratio: 0.5424187304696609
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer to finish
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-6205-v3-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-6205-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: Downloaded to shared memory in 16.476s
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:00, 104.50it/s] Loading 0: 100%|██████████| 291/291 [00:06<00:00, 38.30it/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-6205-v3-mkmlizer: quantized model in 17.793s
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e1.2 in 35.392s
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6205-v3
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6205-v3/special_tokens_map.json
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6205-v3/tokenizer_config.json
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6205-v3/config.json
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6205-v3/tokenizer.json
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6205-v3/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-6205-v3-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-6205-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6205-v3-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-6205-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6205-v3-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-6205-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6205-v3-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-6205-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: Saving duration: 0.256s
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.373s
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6205-v3_reward
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6205-v3_reward/config.json
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6205-v3_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6205-v3_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6205-v3_reward/merges.txt
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6205-v3_reward/vocab.json
cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6205-v3_reward/tokenizer.json
Job cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer completed after 73.84s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-6205-v3-mkmlizer
Pipeline stage MKMLizer completed in 78.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-6205-v3
Waiting for inference service cgato-l3-thespice-8b-dpo-6205-v3 to be ready
Inference service cgato-l3-thespice-8b-dpo-6205-v3 ready after 100.58296251296997s
Pipeline stage ISVCDeployer completed in 109.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.220982789993286s
Received healthy response to inference request in 1.3113768100738525s
Received healthy response to inference request in 1.329313039779663s
Received healthy response to inference request in 1.3412330150604248s
Received healthy response to inference request in 1.289841651916504s
5 requests
0 failed requests
5th percentile: 1.2941486835479736
10th percentile: 1.2984557151794434
20th percentile: 1.3070697784423828
30th percentile: 1.3149640560150146
40th percentile: 1.3221385478973389
50th percentile: 1.329313039779663
60th percentile: 1.3340810298919679
70th percentile: 1.3388490200042724
80th percentile: 1.5171829700469972
90th percentile: 1.8690828800201418
95th percentile: 2.0450328350067135
99th percentile: 2.185792798995972
mean time: 1.498549461364746
Pipeline stage StressChecker completed in 8.13s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dpo_6205_v3 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_6205_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics