submission_id: cgato-l3-thespice-8b-dpo_7538_v3
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e11.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.1, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'You:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s Persona: {memory}\n", 'prompt_template': '***\n{prompt}\n***<|im_end|>\n', 'bot_template': '<|im_start|>{bot_name}\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>{bot_name}\n{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: 2024-05-28T01:17:42+00:00
model_name: cgato-l3-thespice-8b-dpo_7538_v3
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 7026
num_wins: 3698
celo_rating: 1201.03
safety_score: 0.96
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_7538_v3
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e11.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-27
win_ratio: 0.5263307714204384
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer to finish
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-7538-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-7538-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: Downloaded to shared memory in 35.787s
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 87.74it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 101.08it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 145.90it/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-7538-v3-mkmlizer: quantized model in 19.236s
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e11.1 in 56.215s
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7538-v3
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7538-v3/config.json
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7538-v3/special_tokens_map.json
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7538-v3/tokenizer_config.json
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7538-v3/tokenizer.json
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-7538-v3/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-7538-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-7538-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-7538-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-7538-v3-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-7538-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-7538-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: Saving duration: 0.285s
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.712s
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v3_reward
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v3_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v3_reward/config.json
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v3_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v3_reward/merges.txt
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v3_reward/vocab.json
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v3_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-7538-v3_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer completed after 84.16s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-7538-v3-mkmlizer
Pipeline stage MKMLizer completed in 87.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-7538-v3
Waiting for inference service cgato-l3-thespice-8b-dpo-7538-v3 to be ready
Inference service cgato-l3-thespice-8b-dpo-7538-v3 ready after 40.233866930007935s
Pipeline stage ISVCDeployer completed in 47.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3507192134857178s
Received healthy response to inference request in 1.2799129486083984s
Received healthy response to inference request in 1.316462755203247s
Received healthy response to inference request in 1.2812960147857666s
Received healthy response to inference request in 1.319211483001709s
5 requests
0 failed requests
5th percentile: 1.2801895618438721
10th percentile: 1.2804661750793458
20th percentile: 1.281019401550293
30th percentile: 1.2883293628692627
40th percentile: 1.3023960590362549
50th percentile: 1.316462755203247
60th percentile: 1.3175622463226317
70th percentile: 1.3186617374420166
80th percentile: 1.5255130290985108
90th percentile: 1.9381161212921143
95th percentile: 2.144417667388916
99th percentile: 2.3094589042663576
mean time: 1.5095204830169677
Pipeline stage StressChecker completed in 8.21s
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_7538_v3 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_7538_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics