submission_id: cgato-l3-thespice-8b-dpo_6378_v2
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e14.3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, '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{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|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': 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: 2024-06-02T05:37:23+00:00
model_name: cgato-l3-thespice-8b-dpo_6378_v2
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 10457
num_wins: 5646
celo_rating: 1220.73
safety_score: 0.49
propriety_score: 0.6286919831223629
propriety_total_count: 237.0
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_6378_v2
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e14.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.5399254088170603
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer to finish
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-6378-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-6378-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: Downloaded to shared memory in 17.720s
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 83.26it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 96.08it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 138.26it/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-6378-v2-mkmlizer: quantized model in 23.722s
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e14.3 in 44.016s
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6378-v2
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6378-v2/special_tokens_map.json
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6378-v2/tokenizer_config.json
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6378-v2/config.json
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6378-v2/tokenizer.json
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-6378-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-6378-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-6378-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6378-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-6378-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6378-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-6378-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-6378-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-6378-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: Saving duration: 0.409s
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.260s
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v2_reward
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v2_reward/config.json
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v2_reward/merges.txt
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v2_reward/vocab.json
cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-6378-v2_reward/tokenizer.json
Job cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer completed after 73.13s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-6378-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.03s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-6378-v2
Waiting for inference service cgato-l3-thespice-8b-dpo-6378-v2 to be ready
Inference service cgato-l3-thespice-8b-dpo-6378-v2 ready after 40.2484815120697s
Pipeline stage ISVCDeployer completed in 47.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 6.015038967132568s
Received healthy response to inference request in 1.3370373249053955s
Received healthy response to inference request in 1.3165693283081055s
Received healthy response to inference request in 1.311319351196289s
Received healthy response to inference request in 1.3078365325927734s
5 requests
0 failed requests
5th percentile: 1.3085330963134765
10th percentile: 1.3092296600341797
20th percentile: 1.310622787475586
30th percentile: 1.3123693466186523
40th percentile: 1.314469337463379
50th percentile: 1.3165693283081055
60th percentile: 1.3247565269470214
70th percentile: 1.3329437255859375
80th percentile: 2.272637653350831
90th percentile: 4.1438383102417
95th percentile: 5.079438638687133
99th percentile: 5.827918901443481
mean time: 2.257560300827026
Pipeline stage StressChecker completed in 11.93s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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_6378_v2 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_6378_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics