submission_id: cgato-l3-thespice-8b-dp_3142_v14
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e13.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, '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: 2024-06-01T11:00:20+00:00
model_name: cgato-l3-thespice-8b-dp_3142_v14
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 12000
num_wins: 6630
celo_rating: 1211.5
safety_score: 0.94
propriety_score: 0.8
propriety_total_count: 5.0
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-dp_3142_v14
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e13.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.5525
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dp-3142-v14-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dp-3142-v14-mkmlizer to finish
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dp-3142-v14-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-dp-3142-v14-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: Downloaded to shared memory in 16.727s
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 69.69it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 89.87it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 133.23it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: quantized model in 23.411s
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e13.2 in 42.605s
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v14
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v14/config.json
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v14/special_tokens_map.json
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v14/tokenizer_config.json
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v14/tokenizer.json
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v14/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dp-3142-v14-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-dp-3142-v14-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v14-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-dp-3142-v14-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v14-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-dp-3142-v14-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v14-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-dp-3142-v14-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: Saving duration: 0.395s
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.067s
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v14_reward
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v14_reward/config.json
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v14_reward/special_tokens_map.json
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v14_reward/merges.txt
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v14_reward/tokenizer_config.json
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v14_reward/vocab.json
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v14_reward/tokenizer.json
cgato-l3-thespice-8b-dp-3142-v14-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v14_reward/reward.tensors
Job cgato-l3-thespice-8b-dp-3142-v14-mkmlizer completed after 73.05s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dp-3142-v14-mkmlizer
Pipeline stage MKMLizer completed in 82.58s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dp-3142-v14
Waiting for inference service cgato-l3-thespice-8b-dp-3142-v14 to be ready
Inference service cgato-l3-thespice-8b-dp-3142-v14 ready after 40.27727699279785s
Pipeline stage ISVCDeployer completed in 48.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.169245481491089s
Received healthy response to inference request in 1.3078577518463135s
Received healthy response to inference request in 1.314579725265503s
Received healthy response to inference request in 1.2942218780517578s
Received healthy response to inference request in 1.3064320087432861s
5 requests
0 failed requests
5th percentile: 1.2966639041900634
10th percentile: 1.2991059303283692
20th percentile: 1.3039899826049806
30th percentile: 1.3067171573638916
40th percentile: 1.3072874546051025
50th percentile: 1.3078577518463135
60th percentile: 1.3105465412139892
70th percentile: 1.313235330581665
80th percentile: 1.4855128765106203
90th percentile: 1.8273791790008547
95th percentile: 1.9983123302459715
99th percentile: 2.135058851242065
mean time: 1.4784673690795898
Pipeline stage StressChecker completed in 8.28s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dp_3142_v14 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dp_3142_v14 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics