submission_id: turboderp-llama3-turbca_4336_v10
developer_uid: kaltcit
status: inactive
model_repo: turboderp/llama3-turbcat-instruct-8b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.8, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{memory}<|eot_id|>', 'prompt_template': '<|start_header_id|>system<|end_header_id|>\n\n{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: 2024-06-27T19:31:32+00:00
model_name: turboderp-llama3-turbcat
model_group: turboderp/llama3-turbcat
num_battles: 17595
num_wins: 8151
celo_rating: 1162.64
propriety_score: 0.7244403415647358
propriety_total_count: 8666.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: turboderp-llama3-turbcat
ineligible_reason: None
language_model: turboderp/llama3-turbcat-instruct-8b
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-27
win_ratio: 0.4632566069906223
Resubmit model
Running pipeline stage MKMLizer
Starting job with name turboderp-llama3-turbca-4336-v10-mkmlizer
Waiting for job on turboderp-llama3-turbca-4336-v10-mkmlizer to finish
turboderp-llama3-turbca-4336-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ _____ __ __ ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ /___/ ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ Version: 0.8.14 ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ https://mk1.ai ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ The license key for the current software has been verified as ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ belonging to: ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ Chai Research Corp. ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ║ ║
turboderp-llama3-turbca-4336-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
turboderp-llama3-turbca-4336-v10-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.
turboderp-llama3-turbca-4336-v10-mkmlizer: warnings.warn(warning_message, FutureWarning)
Failed to get response for submission blend_jokus_2024-06-27: ('http://mistralai-mixtral-8x7b-3473-v47-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
turboderp-llama3-turbca-4336-v10-mkmlizer: Downloaded to shared memory in 31.418s
turboderp-llama3-turbca-4336-v10-mkmlizer: quantizing model to /dev/shm/model_cache
turboderp-llama3-turbca-4336-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_midur_2024-06-27: ('http://mistralai-mixtral-8x7b-3473-v47-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
turboderp-llama3-turbca-4336-v10-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 106.38it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:02, 99.91it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 117.75it/s] Loading 0: 18%|█▊ | 51/291 [00:00<00:02, 111.15it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 119.15it/s] Loading 0: 27%|██▋ | 78/291 [00:00<00:01, 112.69it/s] Loading 0: 31%|███ | 90/291 [00:01<00:03, 61.76it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:02, 71.66it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:02, 77.32it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 93.86it/s] Loading 0: 48%|████▊ | 141/291 [00:01<00:01, 96.69it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 107.63it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 105.69it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:01, 108.87it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 66.39it/s] Loading 0: 71%|███████ | 206/291 [00:02<00:01, 77.46it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 87.37it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 88.56it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 103.51it/s] Loading 0: 89%|████████▊ | 258/291 [00:02<00:00, 104.28it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 113.74it/s] Loading 0: 98%|█████████▊| 286/291 [00:02<00:00, 115.55it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
turboderp-llama3-turbca-4336-v10-mkmlizer: quantized model in 26.135s
turboderp-llama3-turbca-4336-v10-mkmlizer: Processed model turboderp/llama3-turbcat-instruct-8b in 60.127s
turboderp-llama3-turbca-4336-v10-mkmlizer: creating bucket guanaco-mkml-models
turboderp-llama3-turbca-4336-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
turboderp-llama3-turbca-4336-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v10
turboderp-llama3-turbca-4336-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v10/special_tokens_map.json
turboderp-llama3-turbca-4336-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v10/config.json
turboderp-llama3-turbca-4336-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v10/tokenizer_config.json
turboderp-llama3-turbca-4336-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v10/tokenizer.json
turboderp-llama3-turbca-4336-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/turboderp-llama3-turbca-4336-v10/flywheel_model.0.safetensors
turboderp-llama3-turbca-4336-v10-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
turboderp-llama3-turbca-4336-v10-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.
turboderp-llama3-turbca-4336-v10-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v10-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.
turboderp-llama3-turbca-4336-v10-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v10-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.
turboderp-llama3-turbca-4336-v10-mkmlizer: warnings.warn(
turboderp-llama3-turbca-4336-v10-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()
turboderp-llama3-turbca-4336-v10-mkmlizer: return self.fget.__get__(instance, owner)()
turboderp-llama3-turbca-4336-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
turboderp-llama3-turbca-4336-v10-mkmlizer: Saving duration: 0.459s
turboderp-llama3-turbca-4336-v10-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 14.636s
turboderp-llama3-turbca-4336-v10-mkmlizer: creating bucket guanaco-reward-models
turboderp-llama3-turbca-4336-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
turboderp-llama3-turbca-4336-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v10_reward
turboderp-llama3-turbca-4336-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v10_reward/special_tokens_map.json
turboderp-llama3-turbca-4336-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v10_reward/tokenizer_config.json
turboderp-llama3-turbca-4336-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v10_reward/config.json
turboderp-llama3-turbca-4336-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v10_reward/merges.txt
turboderp-llama3-turbca-4336-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v10_reward/vocab.json
turboderp-llama3-turbca-4336-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v10_reward/tokenizer.json
turboderp-llama3-turbca-4336-v10-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/turboderp-llama3-turbca-4336-v10_reward/reward.tensors
Job turboderp-llama3-turbca-4336-v10-mkmlizer completed after 95.03s with status: succeeded
Stopping job with name turboderp-llama3-turbca-4336-v10-mkmlizer
Pipeline stage MKMLizer completed in 95.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service turboderp-llama3-turbca-4336-v10
Waiting for inference service turboderp-llama3-turbca-4336-v10 to be ready
Inference service turboderp-llama3-turbca-4336-v10 ready after 40.2025887966156s
Pipeline stage ISVCDeployer completed in 47.09s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0691046714782715s
Received healthy response to inference request in 1.2606940269470215s
Received healthy response to inference request in 1.1512255668640137s
Failed to get response for submission blend_jokus_2024-06-27: ('http://alsebay-smaid-v0-1-v5-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:46326->127.0.0.1:8080: read: connection reset by peer\n')
Received healthy response to inference request in 1.1513516902923584s
Received healthy response to inference request in 1.158066749572754s
5 requests
0 failed requests
5th percentile: 1.1512507915496826
10th percentile: 1.1512760162353515
20th percentile: 1.1513264656066895
30th percentile: 1.1526947021484375
40th percentile: 1.1553807258605957
50th percentile: 1.158066749572754
60th percentile: 1.199117660522461
70th percentile: 1.240168571472168
80th percentile: 1.4223761558532717
90th percentile: 1.7457404136657715
95th percentile: 1.9074225425720213
99th percentile: 2.0367682456970213
mean time: 1.3580885410308838
Pipeline stage StressChecker completed in 7.55s
turboderp-llama3-turbca_4336_v10 status is now deployed due to DeploymentManager action
turboderp-llama3-turbca_4336_v10 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics