developer_uid: Hastagaras
submission_id: hastagaras-jametkuproy_v1
model_name: gm
model_group: Hastagaras/JametKuproy
status: torndown
timestamp: 2024-07-01T19:06:02+00:00
num_battles: 12702
num_wins: 6465
celo_rating: 1186.45
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/JametKuproy
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: gm
is_internal_developer: False
language_model: Hastagaras/JametKuproy
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-01
win_ratio: 0.5089749645725082
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jametkuproy-v1-mkmlizer
Waiting for job on hastagaras-jametkuproy-v1-mkmlizer to finish
hastagaras-jametkuproy-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jametkuproy-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-jametkuproy-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jametkuproy-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jametkuproy-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jametkuproy-v1-mkmlizer: ║ /___/ ║
hastagaras-jametkuproy-v1-mkmlizer: ║ ║
hastagaras-jametkuproy-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jametkuproy-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jametkuproy-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-jametkuproy-v1-mkmlizer: ║ ║
hastagaras-jametkuproy-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jametkuproy-v1-mkmlizer: ║ belonging to: ║
hastagaras-jametkuproy-v1-mkmlizer: ║ ║
hastagaras-jametkuproy-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jametkuproy-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jametkuproy-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jametkuproy-v1-mkmlizer: ║ ║
hastagaras-jametkuproy-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jametkuproy-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-jametkuproy-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jametkuproy-v1-mkmlizer: Downloaded to shared memory in 32.840s
hastagaras-jametkuproy-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jametkuproy-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jametkuproy-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 121.74it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 144.34it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 152.18it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 152.82it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 79.13it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 86.69it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 104.01it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 119.03it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 130.95it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 139.26it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 95.32it/s] Loading 0: 69%|██████▉ | 201/291 [00:01<00:00, 103.06it/s] Loading 0: 74%|███████▍ | 216/291 [00:01<00:00, 112.39it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 118.11it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 129.80it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 139.72it/s] Loading 0: 98%|█████████▊| 284/291 [00:02<00:00, 148.60it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jametkuproy-v1-mkmlizer: quantized model in 23.364s
hastagaras-jametkuproy-v1-mkmlizer: Processed model Hastagaras/JametKuproy in 58.828s
hastagaras-jametkuproy-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jametkuproy-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jametkuproy-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jametkuproy-v1
hastagaras-jametkuproy-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jametkuproy-v1/config.json
hastagaras-jametkuproy-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jametkuproy-v1/special_tokens_map.json
hastagaras-jametkuproy-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jametkuproy-v1/tokenizer_config.json
hastagaras-jametkuproy-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jametkuproy-v1/tokenizer.json
hastagaras-jametkuproy-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jametkuproy-v1/flywheel_model.0.safetensors
hastagaras-jametkuproy-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jametkuproy-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-jametkuproy-v1-mkmlizer: warnings.warn(
hastagaras-jametkuproy-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-jametkuproy-v1-mkmlizer: warnings.warn(
hastagaras-jametkuproy-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-jametkuproy-v1-mkmlizer: warnings.warn(
Connection pool is full, discarding connection: %s
hastagaras-jametkuproy-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jametkuproy-v1-mkmlizer: Saving duration: 0.428s
hastagaras-jametkuproy-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.367s
hastagaras-jametkuproy-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jametkuproy-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jametkuproy-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jametkuproy-v1_reward
hastagaras-jametkuproy-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jametkuproy-v1_reward/config.json
hastagaras-jametkuproy-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jametkuproy-v1_reward/special_tokens_map.json
hastagaras-jametkuproy-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jametkuproy-v1_reward/vocab.json
hastagaras-jametkuproy-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jametkuproy-v1_reward/tokenizer_config.json
hastagaras-jametkuproy-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jametkuproy-v1_reward/merges.txt
hastagaras-jametkuproy-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jametkuproy-v1_reward/tokenizer.json
hastagaras-jametkuproy-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jametkuproy-v1_reward/reward.tensors
Job hastagaras-jametkuproy-v1-mkmlizer completed after 83.72s with status: succeeded
Stopping job with name hastagaras-jametkuproy-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.89s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jametkuproy-v1
Waiting for inference service hastagaras-jametkuproy-v1 to be ready
Inference service hastagaras-jametkuproy-v1 ready after 110.56770467758179s
Pipeline stage ISVCDeployer completed in 117.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1071183681488037s
Received healthy response to inference request in 1.1382784843444824s
Received healthy response to inference request in 1.1158504486083984s
Received healthy response to inference request in 1.0955147743225098s
Received healthy response to inference request in 1.1624531745910645s
5 requests
0 failed requests
5th percentile: 1.0995819091796875
10th percentile: 1.1036490440368651
20th percentile: 1.1117833137512207
30th percentile: 1.1203360557556152
40th percentile: 1.1293072700500488
50th percentile: 1.1382784843444824
60th percentile: 1.1479483604431153
70th percentile: 1.157618236541748
80th percentile: 1.3513862133026124
90th percentile: 1.7292522907257082
95th percentile: 1.9181853294372557
99th percentile: 2.0693317604064942
mean time: 1.3238430500030518
Pipeline stage StressChecker completed in 7.56s
hastagaras-jametkuproy_v1 status is now deployed due to DeploymentManager action
hastagaras-jametkuproy_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-jametkuproy_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-jametkuproy-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.98s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-jametkuproy-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-jametkuproy-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-jametkuproy-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-jametkuproy-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-jametkuproy-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-jametkuproy-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-jametkuproy-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-jametkuproy-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-jametkuproy-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-jametkuproy-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-jametkuproy-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-jametkuproy-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.36s
hastagaras-jametkuproy_v1 status is now torndown due to DeploymentManager action