developer_uid: Hastagaras
submission_id: hastagaras-jamet-8b-l3-m_1276_v2
model_name: br1
model_group: Hastagaras/Jamet-8B-L3-M
status: torndown
timestamp: 2024-06-06T13:13:08+00:00
num_battles: 17593
num_wins: 9633
celo_rating: 1218.0
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Jamet-8B-L3-MK.V-BR1
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: br1
is_internal_developer: False
language_model: Hastagaras/Jamet-8B-L3-MK.V-BR1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-06
win_ratio: 0.547547319956801
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 60, '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}
model_eval_status: success
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer to finish
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-1276-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-jamet-8b-l3-m-1276-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: Downloaded to shared memory in 43.341s
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<12:31, 2.60s/it] Loading 0: 3%|▎ | 10/291 [00:05<01:51, 2.51it/s] Loading 0: 5%|▌ | 15/291 [00:05<01:04, 4.25it/s] Loading 0: 10%|▉ | 28/291 [00:05<00:24, 10.52it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:13, 18.31it/s] Loading 0: 19%|█▊ | 54/291 [00:05<00:08, 27.90it/s] Loading 0: 22%|██▏ | 65/291 [00:06<00:09, 25.10it/s] Loading 0: 26%|██▋ | 77/291 [00:06<00:06, 33.84it/s] Loading 0: 31%|███ | 90/291 [00:06<00:04, 45.30it/s] Loading 0: 35%|███▌ | 103/291 [00:06<00:03, 57.55it/s] Loading 0: 39%|███▉ | 114/291 [00:06<00:02, 65.05it/s] Loading 0: 45%|████▍ | 130/291 [00:06<00:01, 82.13it/s] Loading 0: 49%|████▉ | 142/291 [00:06<00:01, 87.43it/s] Loading 0: 54%|█████▍ | 157/291 [00:07<00:01, 100.44it/s] Loading 0: 58%|█████▊ | 170/291 [00:07<00:02, 52.47it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 64.09it/s] Loading 0: 67%|██████▋ | 195/291 [00:07<00:01, 70.72it/s] Loading 0: 73%|███████▎ | 211/291 [00:07<00:00, 86.36it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:00, 91.36it/s] Loading 0: 82%|████████▏ | 238/291 [00:08<00:00, 103.14it/s] Loading 0: 86%|████████▋ | 251/291 [00:08<00:00, 105.61it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 113.01it/s] Loading 0: 96%|█████████▌| 278/291 [00:08<00:00, 59.23it/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-1276-v2-mkmlizer: quantized model in 21.522s
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.V-BR1 in 66.383s
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-1276-v2
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-1276-v2/special_tokens_map.json
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-1276-v2/config.json
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-1276-v2/tokenizer_config.json
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-1276-v2/tokenizer.json
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-1276-v2/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-1276-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-jamet-8b-l3-m-1276-v2-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-1276-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-jamet-8b-l3-m-1276-v2-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-1276-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-jamet-8b-l3-m-1276-v2-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-1276-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-jamet-8b-l3-m-1276-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: Saving duration: 0.265s
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.610s
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-1276-v2_reward
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-1276-v2_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-1276-v2_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-1276-v2_reward/merges.txt
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-1276-v2_reward/config.json
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-1276-v2_reward/vocab.json
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-1276-v2_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-1276-v2_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer completed after 93.51s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-1276-v2-mkmlizer
Pipeline stage MKMLizer completed in 93.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-1276-v2
Waiting for inference service hastagaras-jamet-8b-l3-m-1276-v2 to be ready
Inference service hastagaras-jamet-8b-l3-m-1276-v2 ready after 40.237309217453s
Pipeline stage ISVCDeployer completed in 45.78s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.271516799926758s
Received healthy response to inference request in 1.3709743022918701s
Received healthy response to inference request in 1.327747106552124s
Received healthy response to inference request in 1.3122789859771729s
Received healthy response to inference request in 1.228968620300293s
5 requests
0 failed requests
5th percentile: 1.245630693435669
10th percentile: 1.2622927665710448
20th percentile: 1.295616912841797
30th percentile: 1.315372610092163
40th percentile: 1.3215598583221435
50th percentile: 1.327747106552124
60th percentile: 1.3450379848480225
70th percentile: 1.362328863143921
80th percentile: 1.5510828018188478
90th percentile: 1.9112998008728028
95th percentile: 2.09140830039978
99th percentile: 2.235495100021362
mean time: 1.5022971630096436
Pipeline stage StressChecker completed in 8.12s
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_1276_v2 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_1276_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-jamet-8b-l3-m_1276_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-jamet-8b-l3-m-1276-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.27s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-jamet-8b-l3-m-1276-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-1276-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-1276-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-1276-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-jamet-8b-l3-m-1276-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-jamet-8b-l3-m-1276-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-1276-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-1276-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-1276-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-1276-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-1276-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-jamet-8b-l3-m-1276-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.54s
hastagaras-jamet-8b-l3-m_1276_v2 status is now torndown due to DeploymentManager action