submission_id: hastagaras-anjir-8b-l3-m_4330_v1
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/Anjir-8B-L3-MK.III-B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, '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}
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: 2024-06-09T03:02:29+00:00
model_name: b
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3-M
num_battles: 14068
num_wins: 7683
celo_rating: 1212.45
propriety_score: 0.6684931506849315
propriety_total_count: 1095.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: b
ineligible_reason: None
language_model: Hastagaras/Anjir-8B-L3-MK.III-B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-08
win_ratio: 0.546133067955644
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer to finish
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-m-4330-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.
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: Downloaded to shared memory in 39.072s
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 125.92it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 151.94it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 159.56it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 164.02it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 88.49it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 105.07it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 118.66it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 128.86it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 137.81it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 141.40it/s] Loading 0: 65%|██████▍ | 189/291 [00:01<00:01, 90.61it/s] Loading 0: 70%|██████▉ | 203/291 [00:01<00:00, 99.75it/s] Loading 0: 76%|███████▌ | 221/291 [00:01<00:00, 115.96it/s] Loading 0: 82%|████████▏ | 239/291 [00:01<00:00, 130.20it/s] Loading 0: 88%|████████▊ | 257/291 [00:02<00:00, 140.96it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 149.07it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: quantized model in 22.471s
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: Processed model Hastagaras/Anjir-8B-L3-MK.III-B in 64.061s
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-4330-v1
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-4330-v1/tokenizer_config.json
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-4330-v1/special_tokens_map.json
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-4330-v1/config.json
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-4330-v1/tokenizer.json
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-4330-v1/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-m-4330-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.
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-4330-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.
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-4330-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.
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-4330-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()
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: Saving duration: 0.403s
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.954s
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-4330-v1_reward
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-4330-v1_reward/config.json
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-4330-v1_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-4330-v1_reward/merges.txt
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-4330-v1_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-4330-v1_reward/vocab.json
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-4330-v1_reward/tokenizer.json
hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-4330-v1_reward/reward.tensors
Job hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer completed after 93.41s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-m-4330-v1-mkmlizer
Pipeline stage MKMLizer completed in 97.26s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-m-4330-v1
Waiting for inference service hastagaras-anjir-8b-l3-m-4330-v1 to be ready
Tearing down inference service hastagaras-anjir-8b-l3-m-4330-v1
%s, retrying in %s seconds...
Creating inference service hastagaras-anjir-8b-l3-m-4330-v1
Waiting for inference service hastagaras-anjir-8b-l3-m-4330-v1 to be ready
Inference service hastagaras-anjir-8b-l3-m-4330-v1 ready after 141.0039246082306s
Pipeline stage ISVCDeployer completed in 757.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0310306549072266s
Received healthy response to inference request in 1.3545267581939697s
Received healthy response to inference request in 1.3174231052398682s
Received healthy response to inference request in 1.2840511798858643s
Received healthy response to inference request in 1.2372181415557861s
5 requests
0 failed requests
5th percentile: 1.2465847492218018
10th percentile: 1.2559513568878173
20th percentile: 1.2746845722198485
30th percentile: 1.2907255649566651
40th percentile: 1.3040743350982666
50th percentile: 1.3174231052398682
60th percentile: 1.3322645664215087
70th percentile: 1.3471060276031495
80th percentile: 1.4898275375366212
90th percentile: 1.760429096221924
95th percentile: 1.895729875564575
99th percentile: 2.0039704990386964
mean time: 1.444849967956543
Pipeline stage StressChecker completed in 7.83s
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-anjir-8b-l3-m_4330_v1 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3-m_4330_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-anjir-8b-l3-m_4330_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-anjir-8b-l3-m-4330-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.86s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-anjir-8b-l3-m-4330-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-m-4330-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-m-4330-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-m-4330-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-m-4330-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-anjir-8b-l3-m-4330-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-4330-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-4330-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-4330-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-4330-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-4330-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-m-4330-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.48s
hastagaras-anjir-8b-l3-m_4330_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics