submission_id: cgato-l3-thespice-8b-dpo_5027_v1
developer_uid: c.gato
best_of: 16
celo_rating: 1201.3
display_name: cgato-l3-thespice-8b-dpo_5027_v1
family_friendly_score: 0.0
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}
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}
is_internal_developer: False
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e17.2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
model_name: cgato-l3-thespice-8b-dpo_5027_v1
model_num_parameters: 8030277632.0
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e17.2
model_size: 8B
num_battles: 12118
num_wins: 6432
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': True, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-06-05T01:42:26+00:00
us_pacific_date: 2024-06-04
win_ratio: 0.5307806568740716
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer to finish
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-5027-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-5027-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: Downloaded to shared memory in 30.184s
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 74.28it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 90.02it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 127.57it/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-5027-v1-mkmlizer: quantized model in 23.823s
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e17.2 in 56.641s
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5027-v1
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5027-v1/config.json
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5027-v1/tokenizer_config.json
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5027-v1/tokenizer.json
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5027-v1/special_tokens_map.json
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-5027-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-5027-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-5027-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5027-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-5027-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5027-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-5027-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-5027-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-5027-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: Saving duration: 0.407s
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.547s
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v1_reward
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v1_reward/config.json
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v1_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v1_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v1_reward/vocab.json
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v1_reward/merges.txt
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v1_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-5027-v1_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer completed after 124.17s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-5027-v1-mkmlizer
Pipeline stage MKMLizer completed in 128.90s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-5027-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-5027-v1 to be ready
Inference service cgato-l3-thespice-8b-dpo-5027-v1 ready after 30.19245743751526s
Pipeline stage ISVCDeployer completed in 37.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0139596462249756s
Received healthy response to inference request in 1.2148418426513672s
Received healthy response to inference request in 1.2258226871490479s
Received healthy response to inference request in 1.2408363819122314s
Received healthy response to inference request in 1.2699673175811768s
5 requests
0 failed requests
5th percentile: 1.2170380115509034
10th percentile: 1.2192341804504394
20th percentile: 1.2236265182495116
30th percentile: 1.2288254261016847
40th percentile: 1.234830904006958
50th percentile: 1.2408363819122314
60th percentile: 1.2524887561798095
70th percentile: 1.2641411304473877
80th percentile: 1.4187657833099367
90th percentile: 1.716362714767456
95th percentile: 1.8651611804962156
99th percentile: 1.9841999530792236
mean time: 1.3930855751037599
Pipeline stage StressChecker completed in 7.61s
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_5027_v1 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_5027_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-dpo_5027_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-dpo-5027-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.29s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-5027-v1/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-5027-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-5027-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-5027-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-5027-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-5027-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-5027-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-5027-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-5027-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-5027-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-5027-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-5027-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.76s
cgato-l3-thespice-8b-dpo_5027_v1 status is now torndown due to DeploymentManager action