submission_id: turboderp-llama3-turbcat_4336_v3
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': '<|begin_of_text|><|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: 2024-06-26T18:52:11+00:00
model_name: turboderp-llama3-turbcat_4336_v3
model_group: turboderp/llama3-turbcat
num_battles: 14076
num_wins: 6460
celo_rating: 1163.48
propriety_score: 0.7267660792287995
propriety_total_count: 6639.0
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_4336_v3
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: 2024-06-26
win_ratio: 0.45893719806763283
Resubmit model
Running pipeline stage MKMLizer
Starting job with name turboderp-llama3-turbcat-4336-v3-mkmlizer
Waiting for job on turboderp-llama3-turbcat-4336-v3-mkmlizer to finish
turboderp-llama3-turbcat-4336-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ _____ __ __ ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ /___/ ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ Version: 0.8.14 ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ https://mk1.ai ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ The license key for the current software has been verified as ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ belonging to: ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ Chai Research Corp. ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ║ ║
turboderp-llama3-turbcat-4336-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
turboderp-llama3-turbcat-4336-v3-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-turbcat-4336-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
turboderp-llama3-turbcat-4336-v3-mkmlizer: Downloaded to shared memory in 32.769s
turboderp-llama3-turbcat-4336-v3-mkmlizer: quantizing model to /dev/shm/model_cache
turboderp-llama3-turbcat-4336-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
turboderp-llama3-turbcat-4336-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 3%|▎ | 8/291 [00:00<00:03, 76.62it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:02, 98.57it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 93.78it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:02, 87.90it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:02, 84.20it/s] Loading 0: 20%|██ | 59/291 [00:00<00:02, 85.30it/s] Loading 0: 24%|██▍ | 71/291 [00:00<00:02, 94.13it/s] Loading 0: 28%|██▊ | 81/291 [00:00<00:02, 89.38it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:05, 36.23it/s] Loading 0: 34%|███▍ | 99/291 [00:01<00:04, 42.03it/s] Loading 0: 38%|███▊ | 111/291 [00:01<00:03, 53.20it/s] Loading 0: 41%|████ | 120/291 [00:01<00:02, 59.72it/s] Loading 0: 44%|████▍ | 129/291 [00:02<00:02, 61.87it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 64.80it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 64.92it/s] Loading 0: 56%|█████▌ | 162/291 [00:02<00:01, 81.57it/s] Loading 0: 59%|█████▉ | 173/291 [00:02<00:01, 87.08it/s] Loading 0: 64%|██████▍ | 187/291 [00:03<00:02, 47.20it/s] Loading 0: 67%|██████▋ | 195/291 [00:03<00:01, 48.54it/s] Loading 0: 70%|███████ | 205/291 [00:03<00:01, 56.84it/s] Loading 0: 74%|███████▍ | 216/291 [00:03<00:01, 66.54it/s] Loading 0: 78%|███████▊ | 226/291 [00:03<00:00, 73.43it/s] Loading 0: 81%|████████▏ | 237/291 [00:03<00:00, 80.06it/s] Loading 0: 85%|████████▍ | 247/291 [00:03<00:00, 81.50it/s] Loading 0: 88%|████████▊ | 257/291 [00:03<00:00, 82.11it/s] Loading 0: 91%|█████████▏| 266/291 [00:03<00:00, 81.79it/s] Loading 0: 95%|█████████▍| 275/291 [00:04<00:00, 81.64it/s] Loading 0: 99%|█████████▊| 287/291 [00:10<00:00, 5.26it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
turboderp-llama3-turbcat-4336-v3-mkmlizer: quantized model in 22.876s
turboderp-llama3-turbcat-4336-v3-mkmlizer: Processed model turboderp/llama3-turbcat-instruct-8b in 57.157s
turboderp-llama3-turbcat-4336-v3-mkmlizer: creating bucket guanaco-mkml-models
turboderp-llama3-turbcat-4336-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
turboderp-llama3-turbcat-4336-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/turboderp-llama3-turbcat-4336-v3
turboderp-llama3-turbcat-4336-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/turboderp-llama3-turbcat-4336-v3/config.json
turboderp-llama3-turbcat-4336-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/turboderp-llama3-turbcat-4336-v3/special_tokens_map.json
turboderp-llama3-turbcat-4336-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/turboderp-llama3-turbcat-4336-v3/tokenizer_config.json
turboderp-llama3-turbcat-4336-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/turboderp-llama3-turbcat-4336-v3/tokenizer.json
turboderp-llama3-turbcat-4336-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/turboderp-llama3-turbcat-4336-v3/flywheel_model.0.safetensors
turboderp-llama3-turbcat-4336-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
turboderp-llama3-turbcat-4336-v3-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-turbcat-4336-v3-mkmlizer: warnings.warn(
turboderp-llama3-turbcat-4336-v3-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-turbcat-4336-v3-mkmlizer: warnings.warn(
turboderp-llama3-turbcat-4336-v3-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-turbcat-4336-v3-mkmlizer: warnings.warn(
turboderp-llama3-turbcat-4336-v3-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-turbcat-4336-v3-mkmlizer: return self.fget.__get__(instance, owner)()
turboderp-llama3-turbcat-4336-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
turboderp-llama3-turbcat-4336-v3-mkmlizer: Saving duration: 0.316s
turboderp-llama3-turbcat-4336-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.361s
turboderp-llama3-turbcat-4336-v3-mkmlizer: creating bucket guanaco-reward-models
turboderp-llama3-turbcat-4336-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
turboderp-llama3-turbcat-4336-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v3_reward
turboderp-llama3-turbcat-4336-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v3_reward/config.json
turboderp-llama3-turbcat-4336-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v3_reward/special_tokens_map.json
turboderp-llama3-turbcat-4336-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v3_reward/merges.txt
turboderp-llama3-turbcat-4336-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v3_reward/tokenizer_config.json
turboderp-llama3-turbcat-4336-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v3_reward/vocab.json
turboderp-llama3-turbcat-4336-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v3_reward/tokenizer.json
turboderp-llama3-turbcat-4336-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/turboderp-llama3-turbcat-4336-v3_reward/reward.tensors
Job turboderp-llama3-turbcat-4336-v3-mkmlizer completed after 94.47s with status: succeeded
Stopping job with name turboderp-llama3-turbcat-4336-v3-mkmlizer
Pipeline stage MKMLizer completed in 95.34s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service turboderp-llama3-turbcat-4336-v3
Waiting for inference service turboderp-llama3-turbcat-4336-v3 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service turboderp-llama3-turbcat-4336-v3 ready after 30.238120555877686s
Pipeline stage ISVCDeployer completed in 37.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9925289154052734s
Received healthy response to inference request in 1.1547729969024658s
Received healthy response to inference request in 1.1376793384552002s
Received healthy response to inference request in 1.1511471271514893s
Received healthy response to inference request in 1.1030285358428955s
5 requests
0 failed requests
5th percentile: 1.1099586963653565
10th percentile: 1.1168888568878175
20th percentile: 1.1307491779327392
30th percentile: 1.140372896194458
40th percentile: 1.1457600116729736
50th percentile: 1.1511471271514893
60th percentile: 1.15259747505188
70th percentile: 1.1540478229522706
80th percentile: 1.3223241806030275
90th percentile: 1.6574265480041506
95th percentile: 1.8249777317047118
99th percentile: 1.959018678665161
mean time: 1.307831382751465
Pipeline stage StressChecker completed in 7.34s
turboderp-llama3-turbcat_4336_v3 status is now deployed due to DeploymentManager action
turboderp-llama3-turbcat_4336_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics