submission_id: cgato-l3-thespice-8b-v0-7-2_v2
developer_uid: c.gato
status: torndown
model_repo: cgato/L3-TheSpice-8b-v0.7.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n {bot_name} responds in one line.\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}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n {bot_name} gives single line responses.\n{bot_name} gives short responses.\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: 2024-04-23T05:11:47+00:00
model_name: cgato-l3-thespice-8b-v0-7-2_v2
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-v0.
num_battles: 6783
num_wins: 3698
celo_rating: 1187.83
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-l3-thespice-8b-v0-7-2_v2
ineligible_reason: propriety_total_count < 800
language_model: cgato/L3-TheSpice-8b-v0.7.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-22
win_ratio: 0.545186495650892
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer to finish
Stopping job with name cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer to finish
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-v0-7-2-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-v0-7-2-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: Downloaded to shared memory in 23.341s
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 120.29it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 123.05it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 30.41it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: quantized model in 17.986s
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-v0.7.2 in 42.247s
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-7-2-v2
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-7-2-v2/config.json
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-7-2-v2/special_tokens_map.json
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-7-2-v2/tokenizer_config.json
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-7-2-v2/tokenizer.json
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-7-2-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-v0-7-2-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-v0-7-2-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-7-2-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-v0-7-2-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-7-2-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-v0-7-2-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: Saving duration: 0.277s
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.348s
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-7-2-v2_reward
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-7-2-v2_reward/config.json
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-7-2-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-7-2-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-7-2-v2_reward/merges.txt
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-7-2-v2_reward/vocab.json
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-7-2-v2_reward/tokenizer.json
cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-7-2-v2_reward/reward.tensors
Job cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer completed after 106.91s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-v0-7-2-v2-mkmlizer
Pipeline stage MKMLizer completed in 110.90s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-v0-7-2-v2
Waiting for inference service cgato-l3-thespice-8b-v0-7-2-v2 to be ready
Inference service cgato-l3-thespice-8b-v0-7-2-v2 ready after 40.23445391654968s
Pipeline stage ISVCDeployer completed in 47.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1000709533691406s
Received healthy response to inference request in 1.4516253471374512s
Received healthy response to inference request in 1.3865940570831299s
Received healthy response to inference request in 1.2675607204437256s
Received healthy response to inference request in 1.2763514518737793s
5 requests
0 failed requests
5th percentile: 1.2693188667297364
10th percentile: 1.2710770130157472
20th percentile: 1.2745933055877685
30th percentile: 1.2983999729156495
40th percentile: 1.3424970149993896
50th percentile: 1.3865940570831299
60th percentile: 1.4126065731048585
70th percentile: 1.4386190891265869
80th percentile: 1.7813144683837894
90th percentile: 2.440692710876465
95th percentile: 2.770381832122802
99th percentile: 3.0341331291198728
mean time: 1.6964405059814454
Pipeline stage StressChecker completed in 9.13s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-v0-7-2_v2 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-v0-7-2_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-v0-7-2_v2
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-v0-7-2-v2 is running
Tearing down inference service cgato-l3-thespice-8b-v0-7-2-v2
Toredown service cgato-l3-thespice-8b-v0-7-2-v2
Pipeline stage ISVCDeleter completed in 4.20s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-7-2-v2/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-7-2-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-7-2-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-7-2-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-7-2-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-7-2-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-7-2-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-7-2-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-7-2-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-7-2-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-7-2-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-7-2-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.11s
cgato-l3-thespice-8b-v0-7-2_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics