submission_id: cgato-l3-thespice-8b-dpo_5102_v2
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e12.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 200, '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': True}
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': True}
timestamp: 2024-05-29T00:28:15+00:00
model_name: cgato-l3-thespice-8b-dpo_5102_v2
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 7776
num_wins: 4247
celo_rating: 1213.3
safety_score: 0.84
propriety_score: 0.0
propriety_total_count: 0.0
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_5102_v2
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e12.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-28
win_ratio: 0.5461676954732511
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer to finish
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-5102-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-5102-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: Downloaded to shared memory in 17.342s
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 78.51it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 93.60it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 132.82it/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-5102-v2-mkmlizer: quantized model in 23.795s
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e12.3 in 43.675s
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v2
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v2/config.json
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v2/tokenizer_config.json
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v2/special_tokens_map.json
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v2/tokenizer.json
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5102-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-5102-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-5102-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5102-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-5102-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5102-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-5102-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5102-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-5102-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: Saving duration: 0.397s
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.102s
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v2_reward
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v2_reward/config.json
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v2_reward/vocab.json
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v2_reward/merges.txt
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v2_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5102-v2_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer completed after 73.5s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-5102-v2-mkmlizer
Pipeline stage MKMLizer completed in 77.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-5102-v2
Waiting for inference service cgato-l3-thespice-8b-dpo-5102-v2 to be ready
Inference service cgato-l3-thespice-8b-dpo-5102-v2 ready after 30.19148564338684s
Pipeline stage ISVCDeployer completed in 37.74s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1569671630859375s
Received healthy response to inference request in 1.2347571849822998s
Received healthy response to inference request in 1.2375390529632568s
Received healthy response to inference request in 1.297776222229004s
Received healthy response to inference request in 1.226835012435913s
5 requests
0 failed requests
5th percentile: 1.2284194469451903
10th percentile: 1.2300038814544678
20th percentile: 1.2331727504730225
30th percentile: 1.2353135585784911
40th percentile: 1.236426305770874
50th percentile: 1.2375390529632568
60th percentile: 1.2616339206695557
70th percentile: 1.2857287883758546
80th percentile: 1.4696144104003908
90th percentile: 1.8132907867431642
95th percentile: 1.9851289749145506
99th percentile: 2.12259952545166
mean time: 1.4307749271392822
Pipeline stage StressChecker completed in 7.80s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dpo_5102_v2 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_5102_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics