developer_uid: Hastagaras
submission_id: hastagaras-es-multilingu_2501_v2
model_name: bot
model_group: Hastagaras/ES-Multilingu
status: torndown
timestamp: 2024-05-22T06:34:13+00:00
num_battles: 6817
num_wins: 3703
celo_rating: 1203.02
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: bot
is_internal_developer: False
language_model: Hastagaras/ES-Multilingual-TEST
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-21
win_ratio: 0.5432008214757225
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|>bot<|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|>bot<|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-v2-mkmlizer
Waiting for job on hastagaras-es-multilingu-2501-v2-mkmlizer to finish
hastagaras-es-multilingu-2501-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ /___/ ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ https://mk1.ai ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ belonging to: ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ║ ║
hastagaras-es-multilingu-2501-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-es-multilingu-2501-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-es-multilingu-2501-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-es-multilingu-2501-v2-mkmlizer: Downloaded to shared memory in 21.533s
hastagaras-es-multilingu-2501-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-es-multilingu-2501-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-es-multilingu-2501-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 3/291 [00:00<00:17, 16.44it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:04, 57.47it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 97.09it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:02, 118.01it/s] Loading 0: 21%|██ | 61/291 [00:00<00:01, 121.47it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:01, 126.51it/s] Loading 0: 31%|███ | 90/291 [00:01<00:03, 59.16it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 71.19it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 89.26it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 105.17it/s] Loading 0: 53%|█████▎ | 153/291 [00:01<00:01, 114.29it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:01, 117.84it/s] Loading 0: 64%|██████▎ | 185/291 [00:01<00:00, 133.24it/s] Loading 0: 69%|██████▊ | 200/291 [00:02<00:01, 69.87it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:01, 76.83it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 93.25it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 107.82it/s] Loading 0: 89%|████████▉ | 260/291 [00:02<00:00, 114.97it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 120.88it/s] Loading 0: 99%|█████████▉| 288/291 [00:08<00:00, 8.73it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-es-multilingu-2501-v2-mkmlizer: quantized model in 21.948s
hastagaras-es-multilingu-2501-v2-mkmlizer: Processed model Hastagaras/ES-Multilingual-TEST in 44.579s
hastagaras-es-multilingu-2501-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-es-multilingu-2501-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-es-multilingu-2501-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-es-multilingu-2501-v2
hastagaras-es-multilingu-2501-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-es-multilingu-2501-v2/config.json
hastagaras-es-multilingu-2501-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-es-multilingu-2501-v2/special_tokens_map.json
hastagaras-es-multilingu-2501-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-es-multilingu-2501-v2/tokenizer_config.json
hastagaras-es-multilingu-2501-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-es-multilingu-2501-v2/tokenizer.json
hastagaras-es-multilingu-2501-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-es-multilingu-2501-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-es-multilingu-2501-v2-mkmlizer: warnings.warn(
hastagaras-es-multilingu-2501-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-es-multilingu-2501-v2-mkmlizer: warnings.warn(
hastagaras-es-multilingu-2501-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-es-multilingu-2501-v2-mkmlizer: warnings.warn(
hastagaras-es-multilingu-2501-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-es-multilingu-2501-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-es-multilingu-2501-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-es-multilingu-2501-v2-mkmlizer: Saving duration: 0.277s
hastagaras-es-multilingu-2501-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.924s
hastagaras-es-multilingu-2501-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-es-multilingu-2501-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-es-multilingu-2501-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v2_reward
hastagaras-es-multilingu-2501-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v2_reward/special_tokens_map.json
hastagaras-es-multilingu-2501-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v2_reward/config.json
hastagaras-es-multilingu-2501-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v2_reward/vocab.json
hastagaras-es-multilingu-2501-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v2_reward/tokenizer_config.json
hastagaras-es-multilingu-2501-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v2_reward/merges.txt
hastagaras-es-multilingu-2501-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v2_reward/tokenizer.json
hastagaras-es-multilingu-2501-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-es-multilingu-2501-v2_reward/reward.tensors
Job hastagaras-es-multilingu-2501-v2-mkmlizer completed after 101.02s with status: succeeded
Stopping job with name hastagaras-es-multilingu-2501-v2-mkmlizer
Pipeline stage MKMLizer completed in 106.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-es-multilingu-2501-v2
Waiting for inference service hastagaras-es-multilingu-2501-v2 to be ready
Inference service hastagaras-es-multilingu-2501-v2 ready after 232.76193475723267s
Pipeline stage ISVCDeployer completed in 239.73s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.196814775466919s
Received healthy response to inference request in 1.2439146041870117s
Received healthy response to inference request in 1.3399415016174316s
Received healthy response to inference request in 1.282407283782959s
Received healthy response to inference request in 1.2693133354187012s
5 requests
0 failed requests
5th percentile: 1.2489943504333496
10th percentile: 1.2540740966796875
20th percentile: 1.2642335891723633
30th percentile: 1.2719321250915527
40th percentile: 1.2771697044372559
50th percentile: 1.282407283782959
60th percentile: 1.3054209709167481
70th percentile: 1.328434658050537
80th percentile: 1.5113161563873292
90th percentile: 1.854065465927124
95th percentile: 2.0254401206970214
99th percentile: 2.1625398445129393
mean time: 1.4664783000946044
Pipeline stage StressChecker completed in 8.28s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
hastagaras-es-multilingu_2501_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-es-multilingu_2501_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-es-multilingu_2501_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-es-multilingu-2501-v2 is running
Tearing down inference service hastagaras-es-multilingu-2501-v2
admin requested tearing down of hastagaras-halu-8b-llama_2564_v4
Toredown service hastagaras-es-multilingu-2501-v2
Running pipeline stage ISVCDeleter
Pipeline stage ISVCDeleter completed in 4.41s
Running pipeline stage MKMLModelDeleter
Checking if service hastagaras-halu-8b-llama-2564-v4 is running
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-es-multilingu-2501-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-es-multilingu-2501-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-es-multilingu-2501-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-es-multilingu-2501-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-es-multilingu-2501-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-es-multilingu-2501-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-es-multilingu-2501-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-es-multilingu-2501-v2_reward/reward.tensors from bucket guanaco-reward-models
Tearing down inference service hastagaras-halu-8b-llama-2564-v4
Deleting key hastagaras-es-multilingu-2501-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Toredown service hastagaras-halu-8b-llama-2564-v4
Deleting key hastagaras-es-multilingu-2501-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-es-multilingu-2501-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Pipeline stage ISVCDeleter completed in 4.18s
Deleting key hastagaras-es-multilingu-2501-v2_reward/vocab.json from bucket guanaco-reward-models
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLModelDeleter completed in 4.26s
Cleaning model data from S3
Cleaning model data from model cache
hastagaras-es-multilingu_2501_v2 status is now torndown due to DeploymentManager action