developer_uid: Hastagaras
submission_id: hastagaras-es-multilingu_2501_v1
model_name: testestest
model_group: Hastagaras/ES-Multilingu
status: torndown
timestamp: 2024-05-22T05:18:37+00:00
num_battles: 16379
num_wins: 8973
celo_rating: 1202.89
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/ES-Multilingual-TEST
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: testestest
is_internal_developer: False
language_model: Hastagaras/ES-Multilingual-TEST
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-21
win_ratio: 0.5478356432016607
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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-es-multilingu-2501-v1-mkmlizer
Waiting for job on hastagaras-es-multilingu-2501-v1-mkmlizer to finish
hastagaras-es-multilingu-2501-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ /___/ ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ belonging to: ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ║ ║
hastagaras-es-multilingu-2501-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-es-multilingu-2501-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-es-multilingu-2501-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-es-multilingu-2501-v1-mkmlizer: Downloaded to shared memory in 23.978s
hastagaras-es-multilingu-2501-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-es-multilingu-2501-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-es-multilingu-2501-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 6%|▌ | 18/291 [00:00<00:01, 175.79it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:01, 195.78it/s] Loading 0: 22%|██▏ | 63/291 [00:00<00:01, 210.34it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 97.26it/s] Loading 0: 37%|███▋ | 108/291 [00:00<00:01, 123.59it/s] Loading 0: 45%|████▍ | 130/291 [00:00<00:01, 143.33it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:00, 167.77it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 181.69it/s] Loading 0: 69%|██████▉ | 201/291 [00:01<00:00, 108.71it/s] Loading 0: 76%|███████▌ | 221/291 [00:01<00:00, 124.49it/s] Loading 0: 85%|████████▍ | 246/291 [00:01<00:00, 149.04it/s] Loading 0: 91%|█████████▏| 266/291 [00:01<00:00, 159.87it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 13.68it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-es-multilingu-2501-v1-mkmlizer: quantized model in 17.201s
hastagaras-es-multilingu-2501-v1-mkmlizer: Processed model Hastagaras/ES-Multilingual-TEST in 42.128s
hastagaras-es-multilingu-2501-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-es-multilingu-2501-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-es-multilingu-2501-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-es-multilingu-2501-v1
hastagaras-es-multilingu-2501-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-es-multilingu-2501-v1/tokenizer_config.json
hastagaras-es-multilingu-2501-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-es-multilingu-2501-v1/config.json
hastagaras-es-multilingu-2501-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-es-multilingu-2501-v1/special_tokens_map.json
hastagaras-es-multilingu-2501-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-es-multilingu-2501-v1/tokenizer.json
hastagaras-es-multilingu-2501-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-es-multilingu-2501-v1/flywheel_model.0.safetensors
hastagaras-es-multilingu-2501-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-es-multilingu-2501-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-es-multilingu-2501-v1-mkmlizer: warnings.warn(
hastagaras-es-multilingu-2501-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-es-multilingu-2501-v1-mkmlizer: warnings.warn(
hastagaras-es-multilingu-2501-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-es-multilingu-2501-v1-mkmlizer: warnings.warn(
hastagaras-es-multilingu-2501-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-es-multilingu-2501-v1-mkmlizer: Saving duration: 0.238s
hastagaras-es-multilingu-2501-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.296s
hastagaras-es-multilingu-2501-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-es-multilingu-2501-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-es-multilingu-2501-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v1_reward
hastagaras-es-multilingu-2501-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v1_reward/config.json
hastagaras-es-multilingu-2501-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v1_reward/tokenizer_config.json
hastagaras-es-multilingu-2501-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v1_reward/merges.txt
hastagaras-es-multilingu-2501-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v1_reward/vocab.json
hastagaras-es-multilingu-2501-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v1_reward/tokenizer.json
hastagaras-es-multilingu-2501-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v1_reward/special_tokens_map.json
hastagaras-es-multilingu-2501-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v1_reward/reward.tensors
Job hastagaras-es-multilingu-2501-v1-mkmlizer completed after 74.03s with status: succeeded
Stopping job with name hastagaras-es-multilingu-2501-v1-mkmlizer
Pipeline stage MKMLizer completed in 79.32s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-es-multilingu-2501-v1
Waiting for inference service hastagaras-es-multilingu-2501-v1 to be ready
Inference service hastagaras-es-multilingu-2501-v1 ready after 70.55323624610901s
Pipeline stage ISVCDeployer completed in 78.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.16377329826355s
Received healthy response to inference request in 1.3940424919128418s
Received healthy response to inference request in 1.3323287963867188s
Received healthy response to inference request in 1.3171923160552979s
Received healthy response to inference request in 1.4794433116912842s
5 requests
0 failed requests
5th percentile: 1.3202196121215821
10th percentile: 1.3232469081878662
20th percentile: 1.3293015003204345
30th percentile: 1.3446715354919434
40th percentile: 1.3693570137023925
50th percentile: 1.3940424919128418
60th percentile: 1.4282028198242187
70th percentile: 1.4623631477355956
80th percentile: 1.6163093090057374
90th percentile: 1.8900413036346437
95th percentile: 2.0269073009490963
99th percentile: 2.1364000988006593
mean time: 1.5373560428619384
Pipeline stage StressChecker completed in 8.32s
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-es-multilingu_2501_v1 status is now deployed due to DeploymentManager action
hastagaras-es-multilingu_2501_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-es-multilingu_2501_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-es-multilingu-2501-v1 is running
Tearing down inference service hastagaras-es-multilingu-2501-v1
Toredown service hastagaras-es-multilingu-2501-v1
Pipeline stage ISVCDeleter completed in 3.13s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-es-multilingu-2501-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-es-multilingu-2501-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-es-multilingu-2501-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-es-multilingu-2501-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-es-multilingu-2501-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-es-multilingu-2501-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-es-multilingu-2501-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-es-multilingu-2501-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-es-multilingu-2501-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-es-multilingu-2501-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-es-multilingu-2501-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-es-multilingu-2501-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.18s
hastagaras-es-multilingu_2501_v1 status is now torndown due to DeploymentManager action