developer_uid: Hastagaras
submission_id: hastagaras-sychomet-8b-l_9826_v2
model_name: 1
model_group: Hastagaras/Sychomet-8B-L
status: torndown
timestamp: 2024-06-17T03:42:46+00:00
num_battles: 12472
num_wins: 6678
celo_rating: 1214.51
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Sychomet-8B-L3-MK.I
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: 1
is_internal_developer: False
language_model: Hastagaras/Sychomet-8B-L3-MK.I
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-16
win_ratio: 0.5354393842206543
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 65, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
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}
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-9826-v2-mkmlizer
Waiting for job on hastagaras-sychomet-8b-l-9826-v2-mkmlizer to finish
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ /___/ ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ belonging to: ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ║ ║
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-sychomet-8b-l-9826-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-9826-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: Downloaded to shared memory in 22.583s
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 120.87it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 146.72it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 154.18it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 159.47it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 82.54it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 89.95it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 107.05it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 120.92it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 131.29it/s] Loading 0: 57%|█████▋ | 166/291 [00:01<00:00, 140.84it/s] Loading 0: 64%|██████▎ | 185/291 [00:01<00:00, 152.42it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 90.27it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 104.39it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 117.24it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 128.53it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 138.49it/s] Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 9.89it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: quantized model in 23.158s
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: Processed model Hastagaras/Sychomet-8B-L3-MK.I in 48.228s
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-9826-v2
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-9826-v2/tokenizer_config.json
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-9826-v2/special_tokens_map.json
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-9826-v2/config.json
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-9826-v2/tokenizer.json
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-sychomet-8b-l-9826-v2/flywheel_model.0.safetensors
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-sychomet-8b-l-9826-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-9826-v2-mkmlizer: warnings.warn(
hastagaras-sychomet-8b-l-9826-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-9826-v2-mkmlizer: warnings.warn(
hastagaras-sychomet-8b-l-9826-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-9826-v2-mkmlizer: warnings.warn(
hastagaras-sychomet-8b-l-9826-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-9826-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: Saving duration: 0.410s
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.487s
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-sychomet-8b-l-9826-v2_reward
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-9826-v2_reward/config.json
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-9826-v2_reward/special_tokens_map.json
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-9826-v2_reward/tokenizer_config.json
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-sychomet-8b-l-9826-v2_reward/merges.txt
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-9826-v2_reward/vocab.json
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-sychomet-8b-l-9826-v2_reward/tokenizer.json
hastagaras-sychomet-8b-l-9826-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-sychomet-8b-l-9826-v2_reward/reward.tensors
Job hastagaras-sychomet-8b-l-9826-v2-mkmlizer completed after 73.19s with status: succeeded
Stopping job with name hastagaras-sychomet-8b-l-9826-v2-mkmlizer
Pipeline stage MKMLizer completed in 75.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-sychomet-8b-l-9826-v2
Waiting for inference service hastagaras-sychomet-8b-l-9826-v2 to be ready
Inference service hastagaras-sychomet-8b-l-9826-v2 ready after 502.65906143188477s
Pipeline stage ISVCDeployer completed in 509.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.179097890853882s
Received healthy response to inference request in 1.255627155303955s
Received healthy response to inference request in 1.2554943561553955s
Received healthy response to inference request in 1.2636098861694336s
Received healthy response to inference request in 1.2703890800476074s
5 requests
0 failed requests
5th percentile: 1.2555209159851075
10th percentile: 1.2555474758148193
20th percentile: 1.255600595474243
30th percentile: 1.2572237014770509
40th percentile: 1.2604167938232422
50th percentile: 1.2636098861694336
60th percentile: 1.266321563720703
70th percentile: 1.2690332412719727
80th percentile: 1.4521308422088626
90th percentile: 1.8156143665313722
95th percentile: 1.9973561286926267
99th percentile: 2.1427495384216306
mean time: 1.4448436737060546
Pipeline stage StressChecker completed in 7.79s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.02s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-sychomet-8b-l_9826_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-sychomet-8b-l_9826_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-sychomet-8b-l_9826_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-sychomet-8b-l-9826-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.61s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-sychomet-8b-l-9826-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-sychomet-8b-l-9826-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-sychomet-8b-l-9826-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-sychomet-8b-l-9826-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-sychomet-8b-l-9826-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-sychomet-8b-l-9826-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-9826-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-9826-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-9826-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-9826-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-9826-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-sychomet-8b-l-9826-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.22s
hastagaras-sychomet-8b-l_9826_v2 status is now torndown due to DeploymentManager action