submission_id: trace2333-duduk-llama3-v2_v2
developer_uid: Trace2333
alignment_samples: 0
best_of: 16
celo_rating: 1170.06
display_name: trace2333-duduk-llama3-v2_v2
formatter: {'memory_template': "<|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\nYou: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.05, 'top_p': 0.98, 'min_p': 0.15, 'top_k': 200, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: False
language_model: Trace2333/duduk_llama3_v2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Trace2333/duduk_llama3_v
model_name: trace2333-duduk-llama3-v2_v2
model_num_parameters: 8030261248.0
model_repo: Trace2333/duduk_llama3_v2
model_size: 8B
num_battles: 20509
num_wins: 8979
propriety_score: 0.7391799544419134
propriety_total_count: 878.0
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: Jellywibble/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-24T08:12:06+00:00
us_pacific_date: 2024-07-24
win_ratio: 0.4378077917012044
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name trace2333-duduk-llama3-v2-v2-mkmlizer
Waiting for job on trace2333-duduk-llama3-v2-v2-mkmlizer to finish
trace2333-duduk-llama3-v2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ _____ __ __ ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ /___/ ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ Version: 0.9.6 ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ https://mk1.ai ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ belonging to: ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ Chai Research Corp. ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ║ ║
trace2333-duduk-llama3-v2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-duduk-llama3-v2-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 27.21it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 37.24it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:07, 35.17it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:06, 38.66it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 36.39it/s] Loading 0: 11%|█ | 31/291 [00:00<00:06, 42.92it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 24.51it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 26.69it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 33.78it/s] Loading 0: 18%|█▊ | 53/291 [00:01<00:06, 34.80it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:06, 35.32it/s] Loading 0: 21%|██▏ | 62/291 [00:01<00:06, 36.11it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:06, 36.79it/s] Loading 0: 25%|██▍ | 72/291 [00:02<00:05, 39.27it/s] Loading 0: 26%|██▋ | 77/291 [00:02<00:06, 34.34it/s] Loading 0: 28%|██▊ | 81/291 [00:02<00:08, 26.11it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:07, 27.41it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 31.33it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 30.99it/s] Loading 0: 34%|███▍ | 99/291 [00:02<00:05, 34.64it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 34.10it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:04, 37.17it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:04, 35.85it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:04, 35.86it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 39.81it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 37.99it/s] Loading 0: 46%|████▌ | 133/291 [00:03<00:04, 33.36it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:04, 33.43it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:04, 31.05it/s] Loading 0: 50%|████▉ | 145/291 [00:04<00:04, 32.25it/s] Loading 0: 51%|█████ | 149/291 [00:04<00:04, 29.83it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 37.50it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 35.78it/s] Loading 0: 57%|█████▋ | 165/291 [00:04<00:03, 38.18it/s] Loading 0: 58%|█████▊ | 169/291 [00:04<00:03, 35.82it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 38.05it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 36.14it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 42.17it/s] Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 25.12it/s] Loading 0: 67%|██████▋ | 194/291 [00:05<00:03, 26.80it/s] Loading 0: 69%|██████▉ | 201/291 [00:05<00:02, 33.54it/s] Loading 0: 71%|███████ | 206/291 [00:06<00:02, 34.31it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 35.23it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 34.04it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:01, 36.63it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:01, 35.46it/s] Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 35.82it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:01, 36.11it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 26.91it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:01, 26.83it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 34.85it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 34.08it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:00, 36.75it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 35.29it/s] Loading 0: 91%|█████████ | 264/291 [00:07<00:00, 37.44it/s] Loading 0: 92%|█████████▏| 268/291 [00:07<00:00, 34.77it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 37.87it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 36.27it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 36.01it/s] Loading 0: 98%|█████████▊| 286/291 [00:13<00:01, 2.61it/s] Loading 0: 99%|█████████▉| 289/291 [00:13<00:00, 3.26it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
trace2333-duduk-llama3-v2-v2-mkmlizer: quantized model in 28.214s
trace2333-duduk-llama3-v2-v2-mkmlizer: Processed model Trace2333/duduk_llama3_v2 in 84.874s
trace2333-duduk-llama3-v2-v2-mkmlizer: creating bucket guanaco-mkml-models
trace2333-duduk-llama3-v2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-duduk-llama3-v2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-duduk-llama3-v2-v2
trace2333-duduk-llama3-v2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v2-v2/config.json
trace2333-duduk-llama3-v2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v2-v2/special_tokens_map.json
trace2333-duduk-llama3-v2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v2-v2/tokenizer_config.json
trace2333-duduk-llama3-v2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-duduk-llama3-v2-v2/flywheel_model.0.safetensors
trace2333-duduk-llama3-v2-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-duduk-llama3-v2-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama3-v2-v2-mkmlizer: warnings.warn(
trace2333-duduk-llama3-v2-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama3-v2-v2-mkmlizer: warnings.warn(
trace2333-duduk-llama3-v2-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama3-v2-v2-mkmlizer: warnings.warn(
trace2333-duduk-llama3-v2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-duduk-llama3-v2-v2-mkmlizer: Saving duration: 1.369s
trace2333-duduk-llama3-v2-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.979s
trace2333-duduk-llama3-v2-v2-mkmlizer: creating bucket guanaco-reward-models
trace2333-duduk-llama3-v2-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-duduk-llama3-v2-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v2_reward
trace2333-duduk-llama3-v2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v2_reward/config.json
trace2333-duduk-llama3-v2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v2_reward/special_tokens_map.json
trace2333-duduk-llama3-v2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v2_reward/tokenizer_config.json
trace2333-duduk-llama3-v2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v2_reward/merges.txt
trace2333-duduk-llama3-v2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v2_reward/vocab.json
trace2333-duduk-llama3-v2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v2_reward/tokenizer.json
trace2333-duduk-llama3-v2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v2_reward/reward.tensors
Job trace2333-duduk-llama3-v2-v2-mkmlizer completed after 125.52s with status: succeeded
Stopping job with name trace2333-duduk-llama3-v2-v2-mkmlizer
Pipeline stage MKMLizer completed in 126.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-duduk-llama3-v2-v2
Waiting for inference service trace2333-duduk-llama3-v2-v2 to be ready
Inference service trace2333-duduk-llama3-v2-v2 ready after 80.53949427604675s
Pipeline stage ISVCDeployer completed in 82.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3253278732299805s
Received healthy response to inference request in 1.491623878479004s
Received healthy response to inference request in 1.4398791790008545s
Received healthy response to inference request in 1.4127938747406006s
Received healthy response to inference request in 1.3957176208496094s
5 requests
0 failed requests
5th percentile: 1.3991328716278075
10th percentile: 1.402548122406006
20th percentile: 1.4093786239624024
30th percentile: 1.4182109355926513
40th percentile: 1.429045057296753
50th percentile: 1.4398791790008545
60th percentile: 1.4605770587921143
70th percentile: 1.4812749385833741
80th percentile: 1.6583646774291994
90th percentile: 1.99184627532959
95th percentile: 2.158587074279785
99th percentile: 2.2919797134399413
mean time: 1.6130684852600097
Pipeline stage StressChecker completed in 8.72s
trace2333-duduk-llama3-v2_v2 status is now deployed due to DeploymentManager action
trace2333-duduk-llama3-v2_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-duduk-llama3-v2_v2
Running pipeline stage ISVCDeleter
Checking if service trace2333-duduk-llama3-v2-v2 is running
Tearing down inference service trace2333-duduk-llama3-v2-v2
Service trace2333-duduk-llama3-v2-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.34s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v2-v2/config.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v2-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v2-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v2-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v2-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v2-v2_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v2-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v2-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v2-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v2-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v2-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v2-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.46s
trace2333-duduk-llama3-v2_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics