developer_uid: Hastagaras
submission_id: hastagaras-anjrit_v6
model_name: test
model_group: Hastagaras/anjrit
status: torndown
timestamp: 2024-05-29T09:13:24+00:00
num_battles: 8768
num_wins: 4889
celo_rating: 1212.76
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/anjrit
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: test
is_internal_developer: False
language_model: Hastagaras/anjrit
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-29
win_ratio: 0.557595802919708
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 200, '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': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
model_eval_status: success
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjrit-v6-mkmlizer
Waiting for job on hastagaras-anjrit-v6-mkmlizer to finish
hastagaras-anjrit-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjrit-v6-mkmlizer: ║ _____ __ __ ║
hastagaras-anjrit-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjrit-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjrit-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjrit-v6-mkmlizer: ║ /___/ ║
hastagaras-anjrit-v6-mkmlizer: ║ ║
hastagaras-anjrit-v6-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjrit-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjrit-v6-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjrit-v6-mkmlizer: ║ ║
hastagaras-anjrit-v6-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjrit-v6-mkmlizer: ║ belonging to: ║
hastagaras-anjrit-v6-mkmlizer: ║ ║
hastagaras-anjrit-v6-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjrit-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjrit-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjrit-v6-mkmlizer: ║ ║
hastagaras-anjrit-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjrit-v6-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.
hastagaras-anjrit-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjrit-v6-mkmlizer: Downloaded to shared memory in 53.143s
hastagaras-anjrit-v6-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjrit-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjrit-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:18, 2.35s/it] Loading 0: 5%|▍ | 14/291 [00:04<01:10, 3.93it/s] Loading 0: 9%|▉ | 27/291 [00:04<00:29, 9.00it/s] Loading 0: 14%|█▎ | 40/291 [00:05<00:16, 15.56it/s] Loading 0: 18%|█▊ | 51/291 [00:05<00:10, 22.13it/s] Loading 0: 21%|██▏ | 62/291 [00:05<00:09, 24.64it/s] Loading 0: 26%|██▌ | 76/291 [00:05<00:06, 35.59it/s] Loading 0: 30%|██▉ | 87/291 [00:05<00:04, 43.82it/s] Loading 0: 35%|███▌ | 103/291 [00:05<00:03, 59.99it/s] Loading 0: 40%|███▉ | 115/291 [00:05<00:02, 68.79it/s] Loading 0: 45%|████▍ | 130/291 [00:06<00:01, 83.53it/s] Loading 0: 49%|████▉ | 143/291 [00:06<00:01, 92.76it/s] Loading 0: 54%|█████▍ | 158/291 [00:06<00:01, 101.99it/s] Loading 0: 59%|█████▉ | 171/291 [00:06<00:01, 68.00it/s] Loading 0: 64%|██████▎ | 185/291 [00:06<00:01, 78.61it/s] Loading 0: 68%|██████▊ | 198/291 [00:06<00:01, 88.31it/s] Loading 0: 73%|███████▎ | 212/291 [00:06<00:00, 96.20it/s] Loading 0: 77%|███████▋ | 225/291 [00:07<00:00, 103.66it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:00, 108.05it/s] Loading 0: 87%|████████▋ | 253/291 [00:07<00:00, 114.74it/s] Loading 0: 91%|█████████▏| 266/291 [00:07<00:00, 71.20it/s] Loading 0: 96%|█████████▌| 280/291 [00:07<00:00, 83.39it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjrit-v6-mkmlizer: quantized model in 23.307s
hastagaras-anjrit-v6-mkmlizer: Processed model Hastagaras/anjrit in 78.980s
hastagaras-anjrit-v6-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjrit-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjrit-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjrit-v6
hastagaras-anjrit-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjrit-v6/config.json
hastagaras-anjrit-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjrit-v6/special_tokens_map.json
hastagaras-anjrit-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjrit-v6/tokenizer_config.json
hastagaras-anjrit-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjrit-v6/tokenizer.json
hastagaras-anjrit-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjrit-v6/flywheel_model.0.safetensors
hastagaras-anjrit-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjrit-v6-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.
hastagaras-anjrit-v6-mkmlizer: warnings.warn(
hastagaras-anjrit-v6-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.
hastagaras-anjrit-v6-mkmlizer: warnings.warn(
hastagaras-anjrit-v6-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.
hastagaras-anjrit-v6-mkmlizer: warnings.warn(
hastagaras-anjrit-v6-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()
hastagaras-anjrit-v6-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjrit-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjrit-v6-mkmlizer: Saving duration: 0.877s
hastagaras-anjrit-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 22.553s
hastagaras-anjrit-v6-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjrit-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjrit-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjrit-v6_reward
hastagaras-anjrit-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjrit-v6_reward/config.json
hastagaras-anjrit-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjrit-v6_reward/special_tokens_map.json
hastagaras-anjrit-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjrit-v6_reward/vocab.json
hastagaras-anjrit-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjrit-v6_reward/tokenizer_config.json
hastagaras-anjrit-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjrit-v6_reward/merges.txt
hastagaras-anjrit-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjrit-v6_reward/tokenizer.json
hastagaras-anjrit-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjrit-v6_reward/reward.tensors
Job hastagaras-anjrit-v6-mkmlizer completed after 144.81s with status: succeeded
Stopping job with name hastagaras-anjrit-v6-mkmlizer
Pipeline stage MKMLizer completed in 149.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjrit-v6
Waiting for inference service hastagaras-anjrit-v6 to be ready
Inference service hastagaras-anjrit-v6 ready after 40.233104944229126s
Pipeline stage ISVCDeployer completed in 47.54s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2655627727508545s
Received healthy response to inference request in 1.3789877891540527s
Received healthy response to inference request in 1.3091468811035156s
Received healthy response to inference request in 1.2903804779052734s
Received healthy response to inference request in 1.2714250087738037s
5 requests
0 failed requests
5th percentile: 1.2752161026000977
10th percentile: 1.2790071964263916
20th percentile: 1.2865893840789795
30th percentile: 1.294133758544922
40th percentile: 1.3016403198242188
50th percentile: 1.3091468811035156
60th percentile: 1.3370832443237304
70th percentile: 1.3650196075439454
80th percentile: 1.5563027858734133
90th percentile: 1.9109327793121338
95th percentile: 2.088247776031494
99th percentile: 2.2300997734069825
mean time: 1.5031005859375
Pipeline stage StressChecker completed in 8.14s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-anjrit_v6 status is now deployed due to DeploymentManager action
hastagaras-anjrit_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-anjrit_v6
Running pipeline stage ISVCDeleter
Checking if service hastagaras-anjrit-v6 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.55s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-anjrit-v6/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjrit-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-anjrit-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjrit-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjrit-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-anjrit-v6_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjrit-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-anjrit-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-anjrit-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-anjrit-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-anjrit-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjrit-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.74s
hastagaras-anjrit_v6 status is now torndown due to DeploymentManager action