submission_id: maywell-pivot-10-7b-mist_2379_v1
developer_uid: windyheath
alignment_samples: 0
best_of: 4
celo_rating: 1149.13
display_name: maywell-pivot-10-7b-mist_2379_v1
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}
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': 4, 'max_output_tokens': 64}
ineligible_reason: propriety_total_count < 800
is_internal_developer: False
language_model: maywell/PiVoT-10.7B-Mistral-v0.2-RP
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_eval_status: success
model_group: maywell/PiVoT-10.7B-Mist
model_name: maywell-pivot-10-7b-mist_2379_v1
model_num_parameters: 10731524096.0
model_repo: maywell/PiVoT-10.7B-Mistral-v0.2-RP
model_size: 11B
num_battles: 8794
num_wins: 4117
propriety_score: 0.6946564885496184
propriety_total_count: 655.0
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': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-06-07T20:28:18+00:00
us_pacific_date: 2024-06-07
win_ratio: 0.46816010916534
Resubmit model
Running pipeline stage MKMLizer
Starting job with name maywell-pivot-10-7b-mist-2379-v1-mkmlizer
Waiting for job on maywell-pivot-10-7b-mist-2379-v1-mkmlizer to finish
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ _____ __ __ ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ /___/ ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ Version: 0.8.14 ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ https://mk1.ai ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ The license key for the current software has been verified as ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ belonging to: ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ Chai Research Corp. ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ║ ║
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
maywell-pivot-10-7b-mist-2379-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.
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: Downloaded to shared memory in 64.187s
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: quantizing model to /dev/shm/model_cache
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: quantized model in 21.652s
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: Processed model maywell/PiVoT-10.7B-Mistral-v0.2-RP in 89.254s
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: creating bucket guanaco-mkml-models
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/maywell-pivot-10-7b-mist-2379-v1
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/maywell-pivot-10-7b-mist-2379-v1/special_tokens_map.json
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/maywell-pivot-10-7b-mist-2379-v1/config.json
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/maywell-pivot-10-7b-mist-2379-v1/tokenizer_config.json
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/maywell-pivot-10-7b-mist-2379-v1/tokenizer.model
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/maywell-pivot-10-7b-mist-2379-v1/tokenizer.json
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/maywell-pivot-10-7b-mist-2379-v1/flywheel_model.0.safetensors
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: Loading 0: 0%| | 0/435 [00:00<?, ?it/s] Loading 0: 3%|▎ | 12/435 [00:00<00:05, 76.92it/s] Loading 0: 5%|▍ | 21/435 [00:00<00:05, 78.96it/s] Loading 0: 7%|▋ | 29/435 [00:00<00:05, 73.25it/s] Loading 0: 10%|█ | 45/435 [00:00<00:04, 97.12it/s] Loading 0: 13%|█▎ | 55/435 [00:00<00:03, 97.53it/s] Loading 0: 15%|█▍ | 65/435 [00:00<00:03, 97.14it/s] Loading 0: 19%|█▊ | 81/435 [00:00<00:03, 110.62it/s] Loading 0: 21%|██▏ | 93/435 [00:00<00:03, 104.88it/s] Loading 0: 24%|██▍ | 104/435 [00:01<00:06, 52.56it/s] Loading 0: 28%|██▊ | 120/435 [00:01<00:04, 68.09it/s] Loading 0: 30%|██▉ | 130/435 [00:01<00:04, 73.80it/s] Loading 0: 32%|███▏ | 140/435 [00:01<00:03, 79.13it/s] Loading 0: 36%|███▌ | 155/435 [00:01<00:02, 95.38it/s] Loading 0: 38%|███▊ | 167/435 [00:01<00:02, 89.76it/s] Loading 0: 42%|████▏ | 181/435 [00:02<00:02, 101.50it/s] Loading 0: 44%|████▍ | 193/435 [00:02<00:02, 93.56it/s] Loading 0: 47%|████▋ | 204/435 [00:02<00:03, 62.04it/s] Loading 0: 49%|████▉ | 213/435 [00:02<00:03, 57.03it/s] Loading 0: 52%|█████▏ | 226/435 [00:02<00:02, 70.06it/s] Loading 0: 54%|█████▍ | 237/435 [00:02<00:02, 77.74it/s] Loading 0: 57%|█████▋ | 247/435 [00:03<00:02, 80.65it/s] Loading 0: 59%|█████▉ | 257/435 [00:03<00:02, 84.80it/s] Loading 0: 62%|██████▏ | 270/435 [00:03<00:01, 94.53it/s] Loading 0: 65%|██████▍ | 282/435 [00:03<00:01, 100.66it/s] Loading 0: 67%|██████▋ | 293/435 [00:03<00:01, 89.54it/s] Loading 0: 70%|██████▉ | 304/435 [00:03<00:02, 57.83it/s] Loading 0: 72%|███████▏ | 312/435 [00:04<00:02, 60.51it/s] Loading 0: 75%|███████▍ | 326/435 [00:04<00:01, 76.48it/s] Loading 0: 77%|███████▋ | 336/435 [00:04<00:01, 80.95it/s] Loading 0: 80%|███████▉ | 347/435 [00:04<00:01, 84.15it/s] Loading 0: 83%|████████▎ | 360/435 [00:04<00:00, 95.34it/s] Loading 0: 86%|████████▌ | 373/435 [00:04<00:00, 97.19it/s] Loading 0: 88%|████████▊ | 384/435 [00:04<00:00, 90.77it/s] Loading 0: 91%|█████████ | 394/435 [00:04<00:00, 89.16it/s] Loading 0: 93%|█████████▎| 404/435 [00:06<00:01, 17.68it/s] Loading 0: 95%|█████████▌| 414/435 [00:06<00:00, 22.99it/s] Loading 0: 98%|█████████▊| 427/435 [00:06<00:00, 31.79it/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.
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: warnings.warn(
maywell-pivot-10-7b-mist-2379-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.
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: warnings.warn(
maywell-pivot-10-7b-mist-2379-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.
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: warnings.warn(
maywell-pivot-10-7b-mist-2379-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()
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: return self.fget.__get__(instance, owner)()
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: Saving duration: 0.447s
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.381s
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: creating bucket guanaco-reward-models
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/maywell-pivot-10-7b-mist-2379-v1_reward
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/maywell-pivot-10-7b-mist-2379-v1_reward/tokenizer_config.json
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/maywell-pivot-10-7b-mist-2379-v1_reward/special_tokens_map.json
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/maywell-pivot-10-7b-mist-2379-v1_reward/merges.txt
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/maywell-pivot-10-7b-mist-2379-v1_reward/config.json
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/maywell-pivot-10-7b-mist-2379-v1_reward/vocab.json
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/maywell-pivot-10-7b-mist-2379-v1_reward/tokenizer.json
maywell-pivot-10-7b-mist-2379-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/maywell-pivot-10-7b-mist-2379-v1_reward/reward.tensors
Job maywell-pivot-10-7b-mist-2379-v1-mkmlizer completed after 125.37s with status: succeeded
Stopping job with name maywell-pivot-10-7b-mist-2379-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.74s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service maywell-pivot-10-7b-mist-2379-v1
Waiting for inference service maywell-pivot-10-7b-mist-2379-v1 to be ready
Inference service maywell-pivot-10-7b-mist-2379-v1 ready after 60.35132098197937s
Pipeline stage ISVCDeployer completed in 65.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.344449520111084s
Received healthy response to inference request in 1.5067083835601807s
Received healthy response to inference request in 1.365588903427124s
Received healthy response to inference request in 1.5120797157287598s
Received healthy response to inference request in 1.3021504878997803s
5 requests
0 failed requests
5th percentile: 1.314838171005249
10th percentile: 1.3275258541107178
20th percentile: 1.3529012203216553
30th percentile: 1.3938127994537353
40th percentile: 1.450260591506958
50th percentile: 1.5067083835601807
60th percentile: 1.5088569164276122
70th percentile: 1.511005449295044
80th percentile: 1.6785536766052247
90th percentile: 2.0115015983581546
95th percentile: 2.177975559234619
99th percentile: 2.311154727935791
mean time: 1.6061954021453857
Pipeline stage StressChecker completed in 8.68s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
maywell-pivot-10-7b-mist_2379_v1 status is now deployed due to DeploymentManager action
maywell-pivot-10-7b-mist_2379_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of maywell-pivot-10-7b-mist_2379_v1
Running pipeline stage ISVCDeleter
Checking if service maywell-pivot-10-7b-mist-2379-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.64s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key maywell-pivot-10-7b-mist-2379-v1/config.json from bucket guanaco-mkml-models
Deleting key maywell-pivot-10-7b-mist-2379-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key maywell-pivot-10-7b-mist-2379-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key maywell-pivot-10-7b-mist-2379-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key maywell-pivot-10-7b-mist-2379-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key maywell-pivot-10-7b-mist-2379-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key maywell-pivot-10-7b-mist-2379-v1_reward/config.json from bucket guanaco-reward-models
Deleting key maywell-pivot-10-7b-mist-2379-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key maywell-pivot-10-7b-mist-2379-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key maywell-pivot-10-7b-mist-2379-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key maywell-pivot-10-7b-mist-2379-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key maywell-pivot-10-7b-mist-2379-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key maywell-pivot-10-7b-mist-2379-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 4.00s
maywell-pivot-10-7b-mist_2379_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics