submission_id: thedrummer-llama-3some-8b-v2_v1
developer_uid: Azazelle
best_of: 16
celo_rating: 1208.72
display_name: thedrummer-llama-3some-8b-v2_v1
family_friendly_score: 0.0
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}
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<eot_id>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: TheDrummer/Llama-3SOME-8B-v2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: TheDrummer/Llama-3SOME-8
model_name: thedrummer-llama-3some-8b-v2_v1
model_num_parameters: 8030261248.0
model_repo: TheDrummer/Llama-3SOME-8B-v2
model_size: 8B
num_battles: 30265
num_wins: 16257
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-05T23:58:31+00:00
us_pacific_date: 2024-07-05
win_ratio: 0.5371551296877581
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thedrummer-llama-3some-8b-v2-v1-mkmlizer
Waiting for job on thedrummer-llama-3some-8b-v2-v1-mkmlizer to finish
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ _____ __ __ ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ /___/ ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ Version: 0.8.14 ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ https://mk1.ai ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ belonging to: ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ Chai Research Corp. ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ║ ║
thedrummer-llama-3some-8b-v2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_pefis_2024-07-04: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'min_p\'"}')
thedrummer-llama-3some-8b-v2-v1-mkmlizer: Downloaded to shared memory in 182.617s
thedrummer-llama-3some-8b-v2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
thedrummer-llama-3some-8b-v2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thedrummer-llama-3some-8b-v2-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:48, 2.24s/it] Loading 0: 5%|▌ | 16/291 [00:04<00:57, 4.75it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.69it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.14it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.52it/s] Loading 0: 27%|██▋ | 79/291 [00:05<00:06, 35.01it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 48.98it/s] Loading 0: 39%|███▉ | 113/291 [00:05<00:02, 63.70it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:01, 81.15it/s] Loading 0: 51%|█████ | 149/291 [00:05<00:01, 97.36it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 74.24it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 89.37it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 103.69it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 116.90it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 127.92it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 136.78it/s] Loading 0: 93%|█████████▎| 272/291 [00:06<00:00, 87.22it/s] Loading 0: 99%|█████████▉| 288/291 [00:07<00:00, 99.48it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
thedrummer-llama-3some-8b-v2-v1-mkmlizer: quantized model in 22.702s
thedrummer-llama-3some-8b-v2-v1-mkmlizer: Processed model TheDrummer/Llama-3SOME-8B-v2 in 205.319s
thedrummer-llama-3some-8b-v2-v1-mkmlizer: creating bucket guanaco-mkml-models
thedrummer-llama-3some-8b-v2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thedrummer-llama-3some-8b-v2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thedrummer-llama-3some-8b-v2-v1
thedrummer-llama-3some-8b-v2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thedrummer-llama-3some-8b-v2-v1/config.json
thedrummer-llama-3some-8b-v2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thedrummer-llama-3some-8b-v2-v1/tokenizer_config.json
thedrummer-llama-3some-8b-v2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thedrummer-llama-3some-8b-v2-v1/special_tokens_map.json
thedrummer-llama-3some-8b-v2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thedrummer-llama-3some-8b-v2-v1/tokenizer.json
thedrummer-llama-3some-8b-v2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thedrummer-llama-3some-8b-v2-v1/flywheel_model.0.safetensors
thedrummer-llama-3some-8b-v2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thedrummer-llama-3some-8b-v2-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.
thedrummer-llama-3some-8b-v2-v1-mkmlizer: warnings.warn(
thedrummer-llama-3some-8b-v2-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`.
thedrummer-llama-3some-8b-v2-v1-mkmlizer: warnings.warn(
thedrummer-llama-3some-8b-v2-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.
thedrummer-llama-3some-8b-v2-v1-mkmlizer: warnings.warn(
thedrummer-llama-3some-8b-v2-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.
thedrummer-llama-3some-8b-v2-v1-mkmlizer: warnings.warn(
thedrummer-llama-3some-8b-v2-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()
thedrummer-llama-3some-8b-v2-v1-mkmlizer: return self.fget.__get__(instance, owner)()
thedrummer-llama-3some-8b-v2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thedrummer-llama-3some-8b-v2-v1-mkmlizer: Saving duration: 0.394s
thedrummer-llama-3some-8b-v2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.896s
thedrummer-llama-3some-8b-v2-v1-mkmlizer: creating bucket guanaco-reward-models
thedrummer-llama-3some-8b-v2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thedrummer-llama-3some-8b-v2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thedrummer-llama-3some-8b-v2-v1_reward
thedrummer-llama-3some-8b-v2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thedrummer-llama-3some-8b-v2-v1_reward/config.json
thedrummer-llama-3some-8b-v2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thedrummer-llama-3some-8b-v2-v1_reward/special_tokens_map.json
thedrummer-llama-3some-8b-v2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thedrummer-llama-3some-8b-v2-v1_reward/merges.txt
thedrummer-llama-3some-8b-v2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thedrummer-llama-3some-8b-v2-v1_reward/vocab.json
thedrummer-llama-3some-8b-v2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thedrummer-llama-3some-8b-v2-v1_reward/tokenizer_config.json
thedrummer-llama-3some-8b-v2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thedrummer-llama-3some-8b-v2-v1_reward/tokenizer.json
thedrummer-llama-3some-8b-v2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thedrummer-llama-3some-8b-v2-v1_reward/reward.tensors
Job thedrummer-llama-3some-8b-v2-v1-mkmlizer completed after 268.18s with status: succeeded
Stopping job with name thedrummer-llama-3some-8b-v2-v1-mkmlizer
Pipeline stage MKMLizer completed in 269.07s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service thedrummer-llama-3some-8b-v2-v1
Waiting for inference service thedrummer-llama-3some-8b-v2-v1 to be ready
Inference service thedrummer-llama-3some-8b-v2-v1 ready after 60.38774657249451s
Pipeline stage ISVCDeployer completed in 67.35s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.002591609954834s
Received healthy response to inference request in 1.323556900024414s
Received healthy response to inference request in 1.3042097091674805s
Received healthy response to inference request in 1.2739136219024658s
Received healthy response to inference request in 1.3313379287719727s
5 requests
0 failed requests
5th percentile: 1.2799728393554688
10th percentile: 1.2860320568084718
20th percentile: 1.2981504917144775
30th percentile: 1.308079147338867
40th percentile: 1.3158180236816406
50th percentile: 1.323556900024414
60th percentile: 1.3266693115234376
70th percentile: 1.329781723022461
80th percentile: 1.465588665008545
90th percentile: 1.7340901374816895
95th percentile: 1.8683408737182616
99th percentile: 1.9757414627075196
mean time: 1.4471219539642335
Pipeline stage StressChecker completed in 7.92s
thedrummer-llama-3some-8b-v2_v1 status is now deployed due to DeploymentManager action
thedrummer-llama-3some-8b-v2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of thedrummer-llama-3some-8b-v2_v1
Running pipeline stage ISVCDeleter
Checking if service thedrummer-llama-3some-8b-v2-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.89s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key thedrummer-llama-3some-8b-v2-v1/config.json from bucket guanaco-mkml-models
Deleting key thedrummer-llama-3some-8b-v2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key thedrummer-llama-3some-8b-v2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thedrummer-llama-3some-8b-v2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key thedrummer-llama-3some-8b-v2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key thedrummer-llama-3some-8b-v2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key thedrummer-llama-3some-8b-v2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key thedrummer-llama-3some-8b-v2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key thedrummer-llama-3some-8b-v2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key thedrummer-llama-3some-8b-v2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key thedrummer-llama-3some-8b-v2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key thedrummer-llama-3some-8b-v2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.41s
thedrummer-llama-3some-8b-v2_v1 status is now torndown due to DeploymentManager action