developer_uid: Hastagaras
submission_id: hastagaras-jamet-8b-l3-m_8212_v1
model_name: new-base
model_group: Hastagaras/Jamet-8B-L3-M
status: torndown
timestamp: 2024-06-05T14:10:48+00:00
num_battles: 31736
num_wins: 16701
celo_rating: 1187.96
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Jamet-8B-L3-MK.III-Base
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: new-base
is_internal_developer: False
language_model: Hastagaras/Jamet-8B-L3-MK.III-Base
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-05
win_ratio: 0.5262477943029997
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 1.0, '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: {'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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer to finish
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-8212-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-jamet-8b-l3-m-8212-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: Downloaded to shared memory in 34.956s
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 129.53it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 149.72it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 155.30it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 157.50it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 82.38it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 89.92it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 107.61it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 121.53it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 133.29it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 141.94it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 94.68it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 102.71it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 116.63it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 129.72it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 140.05it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 146.12it/s] Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 10.04it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: quantized model in 22.935s
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.III-Base in 60.486s
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8212-v1
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8212-v1/special_tokens_map.json
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8212-v1/tokenizer_config.json
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8212-v1/config.json
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8212-v1/tokenizer.json
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8212-v1/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-8212-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-jamet-8b-l3-m-8212-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8212-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-jamet-8b-l3-m-8212-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8212-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-jamet-8b-l3-m-8212-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8212-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-jamet-8b-l3-m-8212-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: Saving duration: 0.401s
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.254s
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8212-v1_reward
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8212-v1_reward/config.json
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8212-v1_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8212-v1_reward/merges.txt
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8212-v1_reward/vocab.json
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8212-v1_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8212-v1_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8212-v1_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer completed after 83.38s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-8212-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-8212-v1
Waiting for inference service hastagaras-jamet-8b-l3-m-8212-v1 to be ready
Inference service hastagaras-jamet-8b-l3-m-8212-v1 ready after 40.38630652427673s
Pipeline stage ISVCDeployer completed in 48.51s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1693713665008545s
Received healthy response to inference request in 1.3788275718688965s
Received healthy response to inference request in 1.351283311843872s
Received healthy response to inference request in 1.3388197422027588s
Received healthy response to inference request in 1.278693675994873s
5 requests
0 failed requests
5th percentile: 1.2907188892364503
10th percentile: 1.3027441024780273
20th percentile: 1.3267945289611816
30th percentile: 1.3413124561309815
40th percentile: 1.3462978839874267
50th percentile: 1.351283311843872
60th percentile: 1.3623010158538817
70th percentile: 1.3733187198638916
80th percentile: 1.5369363307952881
90th percentile: 1.8531538486480714
95th percentile: 2.0112626075744626
99th percentile: 2.137749614715576
mean time: 1.503399133682251
Pipeline stage StressChecker completed in 8.22s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-jamet-8b-l3-m_8212_v1 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_8212_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-jamet-8b-l3-m_8212_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-jamet-8b-l3-m-8212-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.35s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-jamet-8b-l3-m-8212-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-8212-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-8212-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-8212-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-8212-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-jamet-8b-l3-m-8212-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-8212-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-8212-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-8212-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-8212-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-8212-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-8212-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.44s
hastagaras-jamet-8b-l3-m_8212_v1 status is now torndown due to DeploymentManager action