developer_uid: Hastagaras
submission_id: hastagaras-sychomet-8b-l_1038_v2
model_name: x
model_group: Hastagaras/Sychomet-8B-L
status: torndown
timestamp: 2024-06-17T06:56:42+00:00
num_battles: 15633
num_wins: 8529
celo_rating: 1214.08
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Sychomet-8B-L3-MK.I-TEST-2
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: x
is_internal_developer: False
language_model: Hastagaras/Sychomet-8B-L3-MK.I-TEST-2
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-16
win_ratio: 0.5455766647476492
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 30, 'presence_penalty': 0.0, 'frequency_penalty': 0.01, 'stopping_words': ['\n', '<|eot_id|>'], '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-sychomet-8b-l-1038-v2-mkmlizer
Waiting for job on hastagaras-sychomet-8b-l-1038-v2-mkmlizer to finish
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ /___/ ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ belonging to: ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ║ ║
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-sychomet-8b-l-1038-v2-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-sychomet-8b-l-1038-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: Downloaded to shared memory in 17.075s
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 117.13it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 143.26it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 151.88it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 153.49it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 79.85it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 87.58it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 105.16it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 119.96it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 132.10it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 140.00it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 91.31it/s] Loading 0: 69%|██████▉ | 201/291 [00:01<00:00, 99.27it/s] Loading 0: 75%|███████▌ | 219/291 [00:01<00:00, 113.50it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 126.16it/s] Loading 0: 88%|████████▊ | 255/291 [00:02<00:00, 136.75it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 144.69it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 9.84it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: quantized model in 23.368s
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: Processed model Hastagaras/Sychomet-8B-L3-MK.I-TEST-2 in 43.073s
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-1038-v2
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-1038-v2/config.json
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-1038-v2/special_tokens_map.json
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-1038-v2/tokenizer_config.json
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-1038-v2/tokenizer.json
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-1038-v2/flywheel_model.0.safetensors
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-sychomet-8b-l-1038-v2-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-sychomet-8b-l-1038-v2-mkmlizer: warnings.warn(
hastagaras-sychomet-8b-l-1038-v2-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-sychomet-8b-l-1038-v2-mkmlizer: warnings.warn(
hastagaras-sychomet-8b-l-1038-v2-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-sychomet-8b-l-1038-v2-mkmlizer: warnings.warn(
hastagaras-sychomet-8b-l-1038-v2-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-sychomet-8b-l-1038-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: Saving duration: 0.421s
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.296s
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v2_reward
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v2_reward/config.json
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v2_reward/special_tokens_map.json
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v2_reward/tokenizer_config.json
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v2_reward/merges.txt
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v2_reward/vocab.json
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v2_reward/tokenizer.json
hastagaras-sychomet-8b-l-1038-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-sychomet-8b-l-1038-v2_reward/reward.tensors
Job hastagaras-sychomet-8b-l-1038-v2-mkmlizer completed after 72.88s with status: succeeded
Stopping job with name hastagaras-sychomet-8b-l-1038-v2-mkmlizer
Pipeline stage MKMLizer completed in 75.72s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-sychomet-8b-l-1038-v2
Waiting for inference service hastagaras-sychomet-8b-l-1038-v2 to be ready
Inference service hastagaras-sychomet-8b-l-1038-v2 ready after 50.32876515388489s
Pipeline stage ISVCDeployer completed in 57.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2794246673583984s
Received healthy response to inference request in 1.4100053310394287s
Received healthy response to inference request in 1.390784740447998s
Received healthy response to inference request in 1.407904863357544s
Received healthy response to inference request in 1.3132028579711914s
5 requests
0 failed requests
5th percentile: 1.3287192344665528
10th percentile: 1.344235610961914
20th percentile: 1.3752683639526366
30th percentile: 1.3942087650299073
40th percentile: 1.4010568141937256
50th percentile: 1.407904863357544
60th percentile: 1.4087450504302979
70th percentile: 1.4095852375030518
80th percentile: 1.5838891983032228
90th percentile: 1.9316569328308106
95th percentile: 2.1055408000946043
99th percentile: 2.24464789390564
mean time: 1.560264492034912
Pipeline stage StressChecker completed in 8.44s
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-sychomet-8b-l_1038_v2 status is now deployed due to DeploymentManager action
hastagaras-sychomet-8b-l_1038_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-sychomet-8b-l_1038_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-sychomet-8b-l-1038-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.18s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-sychomet-8b-l-1038-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-sychomet-8b-l-1038-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-sychomet-8b-l-1038-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-sychomet-8b-l-1038-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-sychomet-8b-l-1038-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-sychomet-8b-l-1038-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-1038-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-1038-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-1038-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-1038-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-1038-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-1038-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.10s
hastagaras-sychomet-8b-l_1038_v2 status is now torndown due to DeploymentManager action