submission_id: grimjim-llama-3-nephilim_9589_v1
developer_uid: grimjim.
status: inactive
model_repo: grimjim/llama-3-Nephilim-v2-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.01, 'top_k': 100, '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': "{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}
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: 2024-07-01T21:21:41+00:00
model_name: grimjim-llama-3-nephilim_9589_v1
model_group: grimjim/llama-3-Nephilim
num_battles: 12662
num_wins: 6663
celo_rating: 1184.54
propriety_score: 0.7204591492234976
propriety_total_count: 5924.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: grimjim-llama-3-nephilim_9589_v1
ineligible_reason: None
language_model: grimjim/llama-3-Nephilim-v2-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-01
win_ratio: 0.5262201863844574
Resubmit model
Running pipeline stage MKMLizer
Starting job with name grimjim-llama-3-nephilim-9589-v1-mkmlizer
Waiting for job on grimjim-llama-3-nephilim-9589-v1-mkmlizer to finish
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ _____ __ __ ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ /___/ ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ Version: 0.8.14 ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ https://mk1.ai ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ The license key for the current software has been verified as ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ belonging to: ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ Chai Research Corp. ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ║ ║
grimjim-llama-3-nephilim-9589-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
grimjim-llama-3-nephilim-9589-v1-mkmlizer: Downloaded to shared memory in 33.580s
grimjim-llama-3-nephilim-9589-v1-mkmlizer: quantizing model to /dev/shm/model_cache
grimjim-llama-3-nephilim-9589-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
grimjim-llama-3-nephilim-9589-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:03, 2.30s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:03, 4.35it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.56it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.78it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:09, 24.95it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 35.79it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 47.46it/s] Loading 0: 39%|███▉ | 113/291 [00:05<00:02, 62.84it/s] Loading 0: 45%|████▍ | 130/291 [00:05<00:02, 77.60it/s] Loading 0: 50%|████▉ | 145/291 [00:05<00:01, 88.62it/s] Loading 0: 55%|█████▍ | 159/291 [00:05<00:01, 96.63it/s] Loading 0: 59%|█████▉ | 173/291 [00:06<00:01, 67.10it/s] Loading 0: 64%|██████▍ | 187/291 [00:06<00:01, 78.95it/s] Loading 0: 70%|███████ | 204/291 [00:06<00:00, 94.57it/s] Loading 0: 76%|███████▋ | 222/291 [00:06<00:00, 103.86it/s] Loading 0: 82%|████████▏ | 239/291 [00:06<00:00, 117.28it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 126.18it/s] Loading 0: 93%|█████████▎| 271/291 [00:07<00:00, 81.06it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 89.61it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
grimjim-llama-3-nephilim-9589-v1-mkmlizer: quantized model in 23.613s
grimjim-llama-3-nephilim-9589-v1-mkmlizer: Processed model grimjim/llama-3-Nephilim-v2-8B in 57.193s
grimjim-llama-3-nephilim-9589-v1-mkmlizer: creating bucket guanaco-mkml-models
grimjim-llama-3-nephilim-9589-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
grimjim-llama-3-nephilim-9589-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/grimjim-llama-3-nephilim-9589-v1
grimjim-llama-3-nephilim-9589-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/grimjim-llama-3-nephilim-9589-v1/tokenizer_config.json
grimjim-llama-3-nephilim-9589-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/grimjim-llama-3-nephilim-9589-v1/special_tokens_map.json
grimjim-llama-3-nephilim-9589-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/grimjim-llama-3-nephilim-9589-v1/config.json
grimjim-llama-3-nephilim-9589-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/grimjim-llama-3-nephilim-9589-v1/tokenizer.json
grimjim-llama-3-nephilim-9589-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/grimjim-llama-3-nephilim-9589-v1/flywheel_model.0.safetensors
grimjim-llama-3-nephilim-9589-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
grimjim-llama-3-nephilim-9589-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.
grimjim-llama-3-nephilim-9589-v1-mkmlizer: warnings.warn(
grimjim-llama-3-nephilim-9589-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`.
grimjim-llama-3-nephilim-9589-v1-mkmlizer: warnings.warn(
grimjim-llama-3-nephilim-9589-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.
grimjim-llama-3-nephilim-9589-v1-mkmlizer: warnings.warn(
grimjim-llama-3-nephilim-9589-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.
grimjim-llama-3-nephilim-9589-v1-mkmlizer: warnings.warn(
grimjim-llama-3-nephilim-9589-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()
grimjim-llama-3-nephilim-9589-v1-mkmlizer: return self.fget.__get__(instance, owner)()
grimjim-llama-3-nephilim-9589-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
grimjim-llama-3-nephilim-9589-v1-mkmlizer: Saving duration: 1.077s
grimjim-llama-3-nephilim-9589-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.692s
grimjim-llama-3-nephilim-9589-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/grimjim-llama-3-nephilim-9589-v1_reward/reward.tensors
Job grimjim-llama-3-nephilim-9589-v1-mkmlizer completed after 93.86s with status: succeeded
Stopping job with name grimjim-llama-3-nephilim-9589-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.81s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service grimjim-llama-3-nephilim-9589-v1
Waiting for inference service grimjim-llama-3-nephilim-9589-v1 to be ready
Inference service grimjim-llama-3-nephilim-9589-v1 ready after 80.39847993850708s
Pipeline stage ISVCDeployer completed in 87.38s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.120537757873535s
Received healthy response to inference request in 1.2486889362335205s
Received healthy response to inference request in 1.2453575134277344s
Received healthy response to inference request in 1.1652991771697998s
Received healthy response to inference request in 1.1181681156158447s
5 requests
0 failed requests
5th percentile: 1.1275943279266358
10th percentile: 1.1370205402374267
20th percentile: 1.1558729648590087
30th percentile: 1.1813108444213867
40th percentile: 1.2133341789245606
50th percentile: 1.2453575134277344
60th percentile: 1.2466900825500489
70th percentile: 1.2480226516723634
80th percentile: 1.4230587005615236
90th percentile: 1.7717982292175294
95th percentile: 1.946167993545532
99th percentile: 2.0856638050079344
mean time: 1.379610300064087
Pipeline stage StressChecker completed in 7.59s
grimjim-llama-3-nephilim_9589_v1 status is now deployed due to DeploymentManager action
grimjim-llama-3-nephilim_9589_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics