submission_id: cgato-l3-thespice-8b-dpo_6827_v2
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e3.1.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 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", 'prompt_template': '***{prompt}\n***<|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: 2024-05-10T18:28:28+00:00
model_name: cgato-l3-thespice-8b-dpo_6827_v2
model_eval_status: pending
double_thumbs_up: 231
thumbs_up: 356
thumbs_down: 180
num_battles: 18653
num_wins: 10092
celo_rating: 1204.81
entertaining: None
stay_in_character: None
user_preference: None
safety_score: 0.79
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_6827_v2
double_thumbs_up_ratio: 0.3011734028683181
feedback_count: 767
ineligible_reason: None
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e3.1.2
model_score: None
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4641460234680574
thumbs_down_ratio: 0.23468057366362452
thumbs_up_ratio: 0.7653194263363755
us_pacific_date: 2024-05-10
win_ratio: 0.5410389749638128
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer to finish
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-6827-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-6827-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: Downloaded to shared memory in 16.876s
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 63.71it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 115.99it/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-6827-v2-mkmlizer: quantized model in 19.888s
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e3.1.2 in 37.695s
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6827-v2
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6827-v2/config.json
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6827-v2/tokenizer_config.json
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6827-v2/special_tokens_map.json
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6827-v2/tokenizer.json
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6827-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-6827-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-6827-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6827-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-6827-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6827-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-6827-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6827-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-6827-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: Saving duration: 0.234s
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.163s
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6827-v2_reward
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6827-v2_reward/config.json
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6827-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6827-v2_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6827-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6827-v2_reward/vocab.json
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6827-v2_reward/merges.txt
cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6827-v2_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer completed after 320.27s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-6827-v2-mkmlizer
Pipeline stage MKMLizer completed in 324.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-6827-v2
Waiting for inference service cgato-l3-thespice-8b-dpo-6827-v2 to be ready
Inference service cgato-l3-thespice-8b-dpo-6827-v2 ready after 30.175102949142456s
Pipeline stage ISVCDeployer completed in 37.78s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1922712326049805s
Received healthy response to inference request in 1.274324655532837s
Received healthy response to inference request in 1.2727322578430176s
Received healthy response to inference request in 1.2926385402679443s
Received healthy response to inference request in 1.2859835624694824s
5 requests
0 failed requests
5th percentile: 1.2730507373809814
10th percentile: 1.2733692169189452
20th percentile: 1.274006175994873
30th percentile: 1.276656436920166
40th percentile: 1.2813199996948241
50th percentile: 1.2859835624694824
60th percentile: 1.2886455535888672
70th percentile: 1.291307544708252
80th percentile: 1.4725650787353517
90th percentile: 1.8324181556701662
95th percentile: 2.012344694137573
99th percentile: 2.156285924911499
mean time: 1.4635900497436523
Pipeline stage StressChecker completed in 7.94s
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-dpo_6827_v2 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_6827_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics