submission_id: cgato-l3-thespice-8b-dpo_3348_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e10.1
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: 2024-05-26T19:23:44+00:00
model_name: cgato-l3-thespice-8b-dpo_3348_v1
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 9210
num_wins: 4896
celo_rating: 1199.88
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_3348_v1
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e10.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-26
win_ratio: 0.5315960912052117
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer to finish
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-3348-v1-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-3348-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: Downloaded to shared memory in 32.483s
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 76.12it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 79.95it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 120.01it/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-3348-v1-mkmlizer: quantized model in 24.215s
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e10.1 in 59.405s
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3348-v1
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3348-v1/config.json
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3348-v1/special_tokens_map.json
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3348-v1/tokenizer_config.json
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3348-v1/tokenizer.json
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3348-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-3348-v1-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-3348-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-3348-v1-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-3348-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-3348-v1-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-3348-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-3348-v1-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-3348-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: Saving duration: 0.448s
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.733s
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3348-v1_reward
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3348-v1_reward/config.json
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3348-v1_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3348-v1_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3348-v1_reward/merges.txt
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3348-v1_reward/vocab.json
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3348-v1_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3348-v1_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer completed after 83.27s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-3348-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.01s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-3348-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-3348-v1 to be ready
Inference service cgato-l3-thespice-8b-dpo-3348-v1 ready after 40.23922085762024s
Pipeline stage ISVCDeployer completed in 46.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2260794639587402s
Received healthy response to inference request in 1.30104398727417s
Received healthy response to inference request in 1.3114371299743652s
Received healthy response to inference request in 3.652028799057007s
%s, retrying in %s seconds...
Received healthy response to inference request in 1.3149666786193848s
Received healthy response to inference request in 1.327195167541504s
Received healthy response to inference request in 1.29764986038208s
Received healthy response to inference request in 1.2707223892211914s
Received healthy response to inference request in 1.2562007904052734s
5 requests
0 failed requests
5th percentile: 1.259105110168457
10th percentile: 1.2620094299316407
20th percentile: 1.267818069458008
30th percentile: 1.2761078834533692
40th percentile: 1.2868788719177247
50th percentile: 1.29764986038208
60th percentile: 1.304576587677002
70th percentile: 1.3115033149719237
80th percentile: 1.3174123764038086
90th percentile: 1.3223037719726562
95th percentile: 1.32474946975708
99th percentile: 1.3267060279846192
mean time: 1.2933469772338868
Pipeline stage StressChecker completed in 35.83s
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_3348_v1 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_3348_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics