submission_id: gryphe-mythomax-l2-13b_v50
developer_uid: Gryphe
status: torndown
model_repo: Gryphe/MythoMax-L2-13b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
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}
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: 2024-05-15T16:44:22+00:00
model_name: gryphe-mythomax-l2-13b_v48
model_eval_status: success
model_group: Gryphe/MythoMax-L2-13b
num_battles: 9789
num_wins: 4584
celo_rating: 1153.53
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 13015864320.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: gryphe-mythomax-l2-13b_v48
ineligible_reason: propriety_total_count < 800
language_model: Gryphe/MythoMax-L2-13b
model_size: 13B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-15
win_ratio: 0.46828072326080294
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name gryphe-mythomax-l2-13b-v50-mkmlizer
Waiting for job on gryphe-mythomax-l2-13b-v50-mkmlizer to finish
gryphe-mythomax-l2-13b-v50-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ _____ __ __ ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ /___/ ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ Version: 0.8.14 ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ https://mk1.ai ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ The license key for the current software has been verified as ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ belonging to: ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ Chai Research Corp. ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ║ ║
gryphe-mythomax-l2-13b-v50-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
gryphe-mythomax-l2-13b-v50-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.
gryphe-mythomax-l2-13b-v50-mkmlizer: warnings.warn(warning_message, FutureWarning)
gryphe-mythomax-l2-13b-v50-mkmlizer: Downloaded to shared memory in 32.877s
gryphe-mythomax-l2-13b-v50-mkmlizer: quantizing model to /dev/shm/model_cache
gryphe-mythomax-l2-13b-v50-mkmlizer: Saving flywheel model at /dev/shm/model_cache
gryphe-mythomax-l2-13b-v50-mkmlizer: quantized model in 23.402s
gryphe-mythomax-l2-13b-v50-mkmlizer: Processed model Gryphe/MythoMax-L2-13b in 60.283s
gryphe-mythomax-l2-13b-v50-mkmlizer: creating bucket guanaco-mkml-models
gryphe-mythomax-l2-13b-v50-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
gryphe-mythomax-l2-13b-v50-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v50
gryphe-mythomax-l2-13b-v50-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v50/config.json
gryphe-mythomax-l2-13b-v50-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v50/added_tokens.json
gryphe-mythomax-l2-13b-v50-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v50/tokenizer_config.json
gryphe-mythomax-l2-13b-v50-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v50/special_tokens_map.json
gryphe-mythomax-l2-13b-v50-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v50/tokenizer.model
gryphe-mythomax-l2-13b-v50-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v50/tokenizer.json
gryphe-mythomax-l2-13b-v50-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v50/flywheel_model.0.safetensors
gryphe-mythomax-l2-13b-v50-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
gryphe-mythomax-l2-13b-v50-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 7%|▋ | 26/363 [00:00<00:05, 59.71it/s] Loading 0: 15%|█▌ | 56/363 [00:00<00:04, 66.54it/s] Loading 0: 24%|██▎ | 86/363 [00:01<00:03, 70.34it/s] Loading 0: 31%|███▏ | 114/363 [00:01<00:03, 68.41it/s] Loading 0: 39%|███▉ | 142/363 [00:02<00:03, 68.74it/s] Loading 0: 47%|████▋ | 170/363 [00:02<00:02, 69.83it/s] Loading 0: 55%|█████▌ | 200/363 [00:02<00:02, 71.48it/s] Loading 0: 63%|██████▎ | 230/363 [00:03<00:01, 73.32it/s] Loading 0: 71%|███████ | 258/363 [00:03<00:01, 72.83it/s] Loading 0: 79%|███████▉ | 286/363 [00:04<00:01, 72.67it/s] Loading 0: 87%|████████▋ | 314/363 [00:04<00:00, 72.74it/s] Loading 0: 95%|█████████▍| 344/363 [00:04<00:00, 78.10it/s] Loading 0: 100%|██████████| 363/363 [00:06<00:00, 35.91it/s] /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.
gryphe-mythomax-l2-13b-v50-mkmlizer: warnings.warn(
gryphe-mythomax-l2-13b-v50-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.
gryphe-mythomax-l2-13b-v50-mkmlizer: warnings.warn(
gryphe-mythomax-l2-13b-v50-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.
gryphe-mythomax-l2-13b-v50-mkmlizer: warnings.warn(
gryphe-mythomax-l2-13b-v50-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()
gryphe-mythomax-l2-13b-v50-mkmlizer: return self.fget.__get__(instance, owner)()
gryphe-mythomax-l2-13b-v50-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
gryphe-mythomax-l2-13b-v50-mkmlizer: Bucket 's3://guanaco-reward-models/' created
gryphe-mythomax-l2-13b-v50-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/gryphe-mythomax-l2-13b-v50_reward
gryphe-mythomax-l2-13b-v50-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/gryphe-mythomax-l2-13b-v50_reward/config.json
gryphe-mythomax-l2-13b-v50-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/gryphe-mythomax-l2-13b-v50_reward/special_tokens_map.json
gryphe-mythomax-l2-13b-v50-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/gryphe-mythomax-l2-13b-v50_reward/tokenizer_config.json
gryphe-mythomax-l2-13b-v50-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/gryphe-mythomax-l2-13b-v50_reward/merges.txt
gryphe-mythomax-l2-13b-v50-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/gryphe-mythomax-l2-13b-v50_reward/vocab.json
gryphe-mythomax-l2-13b-v50-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/gryphe-mythomax-l2-13b-v50_reward/tokenizer.json
gryphe-mythomax-l2-13b-v50-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/gryphe-mythomax-l2-13b-v50_reward/reward.tensors
Job gryphe-mythomax-l2-13b-v50-mkmlizer completed after 94.7s with status: succeeded
Stopping job with name gryphe-mythomax-l2-13b-v50-mkmlizer
Pipeline stage MKMLizer completed in 98.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service gryphe-mythomax-l2-13b-v50
Waiting for inference service gryphe-mythomax-l2-13b-v50 to be ready
Inference service gryphe-mythomax-l2-13b-v50 ready after 40.213846921920776s
Pipeline stage ISVCDeployer completed in 47.87s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.293349266052246s
Received healthy response to inference request in 1.6934561729431152s
Received healthy response to inference request in 1.7150704860687256s
Received healthy response to inference request in 1.7160038948059082s
Received healthy response to inference request in 1.7477507591247559s
5 requests
0 failed requests
5th percentile: 1.6977790355682374
10th percentile: 1.7021018981933593
20th percentile: 1.7107476234436034
30th percentile: 1.715257167816162
40th percentile: 1.7156305313110352
50th percentile: 1.7160038948059082
60th percentile: 1.7287026405334474
70th percentile: 1.7414013862609863
80th percentile: 1.856870460510254
90th percentile: 2.07510986328125
95th percentile: 2.184229564666748
99th percentile: 2.2715253257751464
mean time: 1.8331261157989502
Pipeline stage StressChecker completed in 9.79s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
gryphe-mythomax-l2-13b_v50 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
gryphe-mythomax-l2-13b_v50 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of gryphe-mythomax-l2-13b_v50
Running pipeline stage ISVCDeleter
Checking if service gryphe-mythomax-l2-13b-v50 is running
Tearing down inference service gryphe-mythomax-l2-13b-v50
Toredown service gryphe-mythomax-l2-13b-v50
Pipeline stage ISVCDeleter completed in 4.11s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key gryphe-mythomax-l2-13b-v50/added_tokens.json from bucket guanaco-mkml-models
Deleting key gryphe-mythomax-l2-13b-v50/config.json from bucket guanaco-mkml-models
Deleting key gryphe-mythomax-l2-13b-v50/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key gryphe-mythomax-l2-13b-v50/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key gryphe-mythomax-l2-13b-v50/tokenizer.json from bucket guanaco-mkml-models
Deleting key gryphe-mythomax-l2-13b-v50/tokenizer.model from bucket guanaco-mkml-models
Deleting key gryphe-mythomax-l2-13b-v50/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key gryphe-mythomax-l2-13b-v50_reward/config.json from bucket guanaco-reward-models
Deleting key gryphe-mythomax-l2-13b-v50_reward/merges.txt from bucket guanaco-reward-models
Deleting key gryphe-mythomax-l2-13b-v50_reward/reward.tensors from bucket guanaco-reward-models
Deleting key gryphe-mythomax-l2-13b-v50_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key gryphe-mythomax-l2-13b-v50_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key gryphe-mythomax-l2-13b-v50_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key gryphe-mythomax-l2-13b-v50_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.17s
gryphe-mythomax-l2-13b_v50 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics