submission_id: cgato-l3-thespice-8b-v3-3_v2
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-v3.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s Persona: {memory}<|im_end|>\n", 'prompt_template': '<|im_start|>assistant\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user{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: 2024-05-07T14:50:07+00:00
model_name: cgato-l3-thespice-8b-v3-3_v2
model_eval_status: success
double_thumbs_up: 110
thumbs_up: 187
thumbs_down: 84
num_battles: 13190
num_wins: 6587
celo_rating: 1175.99
entertaining: 6.78
stay_in_character: 8.44
user_preference: 7.1
safety_score: 0.92
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-v3-3_v2
double_thumbs_up_ratio: 0.2887139107611549
feedback_count: 381
ineligible_reason: None
language_model: cgato/L3-TheSpice-8b-v3.3
model_score: 7.44
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.49081364829396323
thumbs_down_ratio: 0.2204724409448819
thumbs_up_ratio: 0.7795275590551181
us_pacific_date: 2024-05-07
win_ratio: 0.499393479909022
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-v3-3-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v3-3-v2-mkmlizer to finish
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-v3-3-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-v3-3-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: Downloaded to shared memory in 28.117s
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 40%|███▉ | 116/291 [00:01<00:01, 115.72it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 118.04it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 27.24it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: quantized model in 23.729s
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-v3.3 in 54.540s
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-3-v2
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-3-v2/config.json
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-3-v2/tokenizer.json
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-3-v2/tokenizer_config.json
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-3-v2/special_tokens_map.json
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-3-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-v3-3-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-v3-3-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v3-3-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-v3-3-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v3-3-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-v3-3-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: Saving duration: 0.403s
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.651s
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v2_reward
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v2_reward/config.json
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v2_reward/merges.txt
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v2_reward/vocab.json
cgato-l3-thespice-8b-v3-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-3-v2_reward/tokenizer.json
Job cgato-l3-thespice-8b-v3-3-v2-mkmlizer completed after 206.62s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-v3-3-v2-mkmlizer
Pipeline stage MKMLizer completed in 213.00s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.15s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-v3-3-v2
Waiting for inference service cgato-l3-thespice-8b-v3-3-v2 to be ready
Inference service cgato-l3-thespice-8b-v3-3-v2 ready after 40.25001859664917s
Pipeline stage ISVCDeployer completed in 49.74s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2997636795043945s
Received healthy response to inference request in 1.2529513835906982s
Received healthy response to inference request in 1.2691459655761719s
Received healthy response to inference request in 1.2608733177185059s
Received healthy response to inference request in 1.2529706954956055s
5 requests
0 failed requests
5th percentile: 1.2529552459716797
10th percentile: 1.2529591083526612
20th percentile: 1.252966833114624
30th percentile: 1.2545512199401856
40th percentile: 1.2577122688293456
50th percentile: 1.2608733177185059
60th percentile: 1.2641823768615723
70th percentile: 1.2674914360046388
80th percentile: 1.4752695083618166
90th percentile: 1.8875165939331056
95th percentile: 2.09364013671875
99th percentile: 2.2585389709472654
mean time: 1.4671410083770753
Pipeline stage StressChecker completed in 8.02s
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-v3-3_v2 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-v3-3_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics