submission_id: hastagaras-bebi-masuk-ne_2222_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/BEBI-MASUK-NELAS-kayanya
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.075, 'top_k': 65, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, '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: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-07-09T23:55:18+00:00
model_name: hastagaras-bebi-masuk-ne_2222_v1
model_group: Hastagaras/BEBI-MASUK-NE
num_battles: 32270
num_wins: 17441
celo_rating: 1217.12
propriety_score: 0.6994525547445255
propriety_total_count: 5480.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-bebi-masuk-ne_2222_v1
ineligible_reason: None
language_model: Hastagaras/BEBI-MASUK-NELAS-kayanya
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-09
win_ratio: 0.5404710257204834
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-bebi-masuk-ne-2222-v1-mkmlizer
Waiting for job on hastagaras-bebi-masuk-ne-2222-v1-mkmlizer to finish
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ /___/ ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ belonging to: ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ║ ║
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: Downloaded to shared memory in 75.236s
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<13:25, 2.79s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:22, 3.34it/s] Loading 0: 10%|▉ | 29/291 [00:05<00:31, 8.38it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:18, 13.58it/s] Loading 0: 19%|█▉ | 56/291 [00:05<00:10, 22.12it/s] Loading 0: 24%|██▎ | 69/291 [00:06<00:09, 23.57it/s] Loading 0: 29%|██▉ | 85/291 [00:06<00:05, 34.67it/s] Loading 0: 33%|███▎ | 97/291 [00:06<00:04, 42.65it/s] Loading 0: 38%|███▊ | 112/291 [00:06<00:03, 55.83it/s] Loading 0: 43%|████▎ | 124/291 [00:06<00:02, 64.69it/s] Loading 0: 48%|████▊ | 139/291 [00:07<00:01, 79.73it/s] Loading 0: 52%|█████▏ | 152/291 [00:07<00:01, 88.30it/s] Loading 0: 57%|█████▋ | 166/291 [00:07<00:02, 56.22it/s] Loading 0: 61%|██████ | 177/291 [00:07<00:01, 63.96it/s] Loading 0: 66%|██████▋ | 193/291 [00:07<00:01, 80.90it/s] Loading 0: 70%|███████ | 205/291 [00:07<00:00, 86.89it/s] Loading 0: 76%|███████▌ | 220/291 [00:07<00:00, 100.62it/s] Loading 0: 80%|████████ | 233/291 [00:08<00:00, 105.91it/s] Loading 0: 85%|████████▍ | 247/291 [00:08<00:00, 109.20it/s] Loading 0: 89%|████████▉ | 260/291 [00:08<00:00, 109.98it/s] Loading 0: 93%|█████████▎| 272/291 [00:08<00:00, 61.13it/s] Loading 0: 98%|█████████▊| 284/291 [00:08<00:00, 69.86it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: quantized model in 28.810s
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: Processed model Hastagaras/BEBI-MASUK-NELAS-kayanya in 104.047s
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-bebi-masuk-ne-2222-v1
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-bebi-masuk-ne-2222-v1/special_tokens_map.json
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-bebi-masuk-ne-2222-v1/tokenizer_config.json
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-bebi-masuk-ne-2222-v1/config.json
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-bebi-masuk-ne-2222-v1/tokenizer.json
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-bebi-masuk-ne-2222-v1/flywheel_model.0.safetensors
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: warnings.warn(
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: warnings.warn(
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: warnings.warn(
hastagaras-bebi-masuk-ne-2222-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-bebi-masuk-ne-2222-v1-mkmlizer: warnings.warn(
hastagaras-bebi-masuk-ne-2222-v1-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-bebi-masuk-ne-2222-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: Saving duration: 0.497s
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.471s
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-bebi-masuk-ne-2222-v1_reward
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-bebi-masuk-ne-2222-v1_reward/config.json
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-bebi-masuk-ne-2222-v1_reward/special_tokens_map.json
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-bebi-masuk-ne-2222-v1_reward/tokenizer_config.json
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-bebi-masuk-ne-2222-v1_reward/vocab.json
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-bebi-masuk-ne-2222-v1_reward/merges.txt
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-bebi-masuk-ne-2222-v1_reward/tokenizer.json
hastagaras-bebi-masuk-ne-2222-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-bebi-masuk-ne-2222-v1_reward/reward.tensors
Job hastagaras-bebi-masuk-ne-2222-v1-mkmlizer completed after 139.5s with status: succeeded
Stopping job with name hastagaras-bebi-masuk-ne-2222-v1-mkmlizer
Pipeline stage MKMLizer completed in 140.53s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-bebi-masuk-ne-2222-v1
Waiting for inference service hastagaras-bebi-masuk-ne-2222-v1 to be ready
Inference service hastagaras-bebi-masuk-ne-2222-v1 ready after 40.19323229789734s
Pipeline stage ISVCDeployer completed in 47.30s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0521039962768555s
Received healthy response to inference request in 1.3595681190490723s
Received healthy response to inference request in 1.3150997161865234s
Received healthy response to inference request in 1.2882120609283447s
Received healthy response to inference request in 1.3617095947265625s
5 requests
0 failed requests
5th percentile: 1.2935895919799805
10th percentile: 1.2989671230316162
20th percentile: 1.3097221851348877
30th percentile: 1.3239933967590332
40th percentile: 1.3417807579040528
50th percentile: 1.3595681190490723
60th percentile: 1.3604247093200683
70th percentile: 1.3612812995910644
80th percentile: 1.4997884750366213
90th percentile: 1.7759462356567384
95th percentile: 1.9140251159667967
99th percentile: 2.0244882202148435
mean time: 1.4753386974334717
Pipeline stage StressChecker completed in 8.15s
hastagaras-bebi-masuk-ne_2222_v1 status is now deployed due to DeploymentManager action
hastagaras-bebi-masuk-ne_2222_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics