developer_uid: Hastagaras
submission_id: hastagaras-jamet-8b-l3-_8630_v10
model_name: turu
model_group: Hastagaras/Jamet-8B-L3-M
status: torndown
timestamp: 2024-06-15T01:28:12+00:00
num_battles: 14208
num_wins: 7546
celo_rating: 1218.0
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
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: turu
is_internal_developer: False
language_model: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-14
win_ratio: 0.5311092342342343
generation_params: {'temperature': 1.05, '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: {'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-l3-8630-v10-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-8630-v10-mkmlizer to finish
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-8630-v10-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-l3-8630-v10-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: Downloaded to shared memory in 16.983s
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 129.79it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 147.80it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 152.06it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 157.21it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 91.74it/s] Loading 0: 33%|███▎ | 97/291 [00:00<00:01, 102.26it/s] Loading 0: 39%|███▉ | 113/291 [00:00<00:01, 113.82it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 127.72it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 137.21it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:00, 144.35it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:00, 141.86it/s] Loading 0: 67%|██████▋ | 196/291 [00:01<00:01, 89.14it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 101.74it/s] Loading 0: 79%|███████▉ | 230/291 [00:01<00:00, 116.67it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 129.24it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 137.43it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 142.21it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: quantized model in 22.680s
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.V-Blackroot in 42.120s
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-8630-v10
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-8630-v10/tokenizer_config.json
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-8630-v10/config.json
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-8630-v10/tokenizer.json
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-8630-v10/special_tokens_map.json
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-8630-v10/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-8630-v10-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-l3-8630-v10-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-8630-v10-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-l3-8630-v10-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-8630-v10-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-l3-8630-v10-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-8630-v10-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-l3-8630-v10-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: Saving duration: 0.391s
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.170s
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-8630-v10_reward
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-8630-v10_reward/config.json
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-8630-v10_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-8630-v10_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-8630-v10_reward/tokenizer.json
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-8630-v10_reward/vocab.json
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-8630-v10_reward/merges.txt
hastagaras-jamet-8b-l3-8630-v10-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-8630-v10_reward/reward.tensors
Job hastagaras-jamet-8b-l3-8630-v10-mkmlizer completed after 73.66s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-8630-v10-mkmlizer
Pipeline stage MKMLizer completed in 77.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-8630-v10
Waiting for inference service hastagaras-jamet-8b-l3-8630-v10 to be ready
Inference service hastagaras-jamet-8b-l3-8630-v10 ready after 40.26145696640015s
Pipeline stage ISVCDeployer completed in 47.79s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.181671380996704s
Received healthy response to inference request in 1.3484697341918945s
Received healthy response to inference request in 1.344928503036499s
Received healthy response to inference request in 1.2811236381530762s
Received healthy response to inference request in 1.2486271858215332s
5 requests
0 failed requests
5th percentile: 1.2551264762878418
10th percentile: 1.2616257667541504
20th percentile: 1.2746243476867676
30th percentile: 1.2938846111297608
40th percentile: 1.31940655708313
50th percentile: 1.344928503036499
60th percentile: 1.3463449954986573
70th percentile: 1.3477614879608155
80th percentile: 1.5151100635528567
90th percentile: 1.8483907222747804
95th percentile: 2.015031051635742
99th percentile: 2.1483433151245115
mean time: 1.4809640884399413
Pipeline stage StressChecker completed in 8.03s
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-_8630_v10 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-_8630_v10 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-jamet-8b-l3-_8630_v10
Running pipeline stage ISVCDeleter
Checking if service hastagaras-jamet-8b-l3-8630-v10 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.20s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-jamet-8b-l3-8630-v10/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-8630-v10/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-8630-v10/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-8630-v10/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-8630-v10/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-jamet-8b-l3-8630-v10_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-8630-v10_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-8630-v10_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-8630-v10_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-8630-v10_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-8630-v10_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-8630-v10_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.46s
hastagaras-jamet-8b-l3-_8630_v10 status is now torndown due to DeploymentManager action