submission_id: meta-llama-meta-llama-3-8b_v8
developer_uid: Meliodia
alignment_samples: 0
best_of: 8
celo_rating: 1160.08
display_name: meta-base-model
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}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: True
language_model: meta-llama/Meta-Llama-3-8B
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: meta-llama/Meta-Llama-3-
model_name: meta-base-model
model_num_parameters: 8030261248.0
model_repo: meta-llama/Meta-Llama-3-8B
model_size: 8B
num_battles: 12107
num_wins: 5501
propriety_score: 0.7250453720508166
propriety_total_count: 1102.0
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: ChaiML/gpt2_medium_pairwise_60m_step_937500
status: torndown
submission_type: basic
timestamp: 2024-07-26T15:49:59+00:00
us_pacific_date: 2024-07-26
win_ratio: 0.45436524324770794
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meta-llama-meta-llama-3-8b-v8-mkmlizer
Waiting for job on meta-llama-meta-llama-3-8b-v8-mkmlizer to finish
meta-llama-meta-llama-3-8b-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ _____ __ __ ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ /___/ ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ Version: 0.9.7 ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ https://mk1.ai ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ The license key for the current software has been verified as ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ belonging to: ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ Chai Research Corp. ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ║ ║
meta-llama-meta-llama-3-8b-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meta-llama-meta-llama-3-8b-v8-mkmlizer: Downloaded to shared memory in 34.665s
meta-llama-meta-llama-3-8b-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkz4swsv3, device:0
meta-llama-meta-llama-3-8b-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meta-llama-meta-llama-3-8b-v8-mkmlizer: quantized model in 26.082s
meta-llama-meta-llama-3-8b-v8-mkmlizer: Processed model meta-llama/Meta-Llama-3-8B in 60.747s
meta-llama-meta-llama-3-8b-v8-mkmlizer: creating bucket guanaco-mkml-models
meta-llama-meta-llama-3-8b-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meta-llama-meta-llama-3-8b-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v8
meta-llama-meta-llama-3-8b-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v8/config.json
meta-llama-meta-llama-3-8b-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v8/special_tokens_map.json
meta-llama-meta-llama-3-8b-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v8/tokenizer_config.json
meta-llama-meta-llama-3-8b-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v8/tokenizer.json
meta-llama-meta-llama-3-8b-v8-mkmlizer: loading reward model from ChaiML/gpt2_medium_pairwise_60m_step_937500
meta-llama-meta-llama-3-8b-v8-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:07, 37.13it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 58.98it/s] Loading 0: 7%|▋ | 20/291 [00:00<00:04, 54.51it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:04, 53.49it/s] Loading 0: 11%|█ | 32/291 [00:00<00:05, 45.04it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:04, 54.30it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:04, 49.10it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:04, 51.30it/s] Loading 0: 20%|██ | 59/291 [00:01<00:04, 47.26it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 53.86it/s] Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 49.59it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:04, 50.95it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:05, 37.12it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:05, 37.64it/s] Loading 0: 33%|███▎ | 96/291 [00:02<00:04, 39.27it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 44.83it/s] Loading 0: 37%|███▋ | 109/291 [00:02<00:04, 43.47it/s] Loading 0: 39%|███▉ | 114/291 [00:02<00:04, 43.60it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 48.83it/s] Loading 0: 44%|████▎ | 127/291 [00:02<00:03, 46.05it/s] Loading 0: 45%|████▌ | 132/291 [00:02<00:03, 45.23it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:03, 49.86it/s] Loading 0: 50%|████▉ | 145/291 [00:03<00:03, 46.60it/s] Loading 0: 52%|█████▏ | 150/291 [00:03<00:03, 44.22it/s] Loading 0: 53%|█████▎ | 155/291 [00:03<00:03, 41.93it/s] Loading 0: 55%|█████▍ | 160/291 [00:03<00:03, 40.29it/s] Loading 0: 57%|█████▋ | 165/291 [00:03<00:03, 41.40it/s] Loading 0: 58%|█████▊ | 170/291 [00:03<00:02, 42.99it/s] Loading 0: 61%|██████ | 177/291 [00:03<00:02, 44.34it/s] Loading 0: 63%|██████▎ | 182/291 [00:03<00:02, 44.18it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:03, 33.34it/s] Loading 0: 66%|██████▌ | 192/291 [00:04<00:02, 35.93it/s] Loading 0: 68%|██████▊ | 197/291 [00:04<00:02, 39.11it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 41.73it/s] Loading 0: 71%|███████▏ | 208/291 [00:04<00:01, 42.36it/s] Loading 0: 73%|███████▎ | 213/291 [00:04<00:01, 42.22it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 47.53it/s] Loading 0: 78%|███████▊ | 226/291 [00:05<00:01, 46.11it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 45.93it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 51.61it/s] Loading 0: 84%|████████▍ | 244/291 [00:05<00:00, 48.26it/s] Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 48.03it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 52.56it/s] Loading 0: 90%|█████████ | 262/291 [00:05<00:00, 47.81it/s] Loading 0: 92%|█████████▏| 267/291 [00:05<00:00, 46.23it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 50.91it/s] Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 45.14it/s] Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 44.87it/s] Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 3.26it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
meta-llama-meta-llama-3-8b-v8-mkmlizer: warnings.warn(
meta-llama-meta-llama-3-8b-v8-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
meta-llama-meta-llama-3-8b-v8-mkmlizer: warnings.warn(
meta-llama-meta-llama-3-8b-v8-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.
meta-llama-meta-llama-3-8b-v8-mkmlizer: warnings.warn(
meta-llama-meta-llama-3-8b-v8-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meta-llama-meta-llama-3-8b-v8-mkmlizer: Saving duration: 0.331s
meta-llama-meta-llama-3-8b-v8-mkmlizer: Processed model ChaiML/gpt2_medium_pairwise_60m_step_937500 in 5.799s
meta-llama-meta-llama-3-8b-v8-mkmlizer: creating bucket guanaco-reward-models
meta-llama-meta-llama-3-8b-v8-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meta-llama-meta-llama-3-8b-v8-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meta-llama-meta-llama-3-8b-v8_reward
meta-llama-meta-llama-3-8b-v8-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meta-llama-meta-llama-3-8b-v8_reward/config.json
meta-llama-meta-llama-3-8b-v8-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meta-llama-meta-llama-3-8b-v8_reward/special_tokens_map.json
meta-llama-meta-llama-3-8b-v8-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meta-llama-meta-llama-3-8b-v8_reward/tokenizer_config.json
meta-llama-meta-llama-3-8b-v8-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meta-llama-meta-llama-3-8b-v8_reward/merges.txt
meta-llama-meta-llama-3-8b-v8-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meta-llama-meta-llama-3-8b-v8_reward/vocab.json
meta-llama-meta-llama-3-8b-v8-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meta-llama-meta-llama-3-8b-v8_reward/tokenizer.json
Job meta-llama-meta-llama-3-8b-v8-mkmlizer completed after 95.06s with status: succeeded
Stopping job with name meta-llama-meta-llama-3-8b-v8-mkmlizer
Pipeline stage MKMLizer completed in 95.93s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service meta-llama-meta-llama-3-8b-v8
Waiting for inference service meta-llama-meta-llama-3-8b-v8 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service meta-llama-meta-llama-3-8b-v8 ready after 80.55234980583191s
Pipeline stage ISVCDeployer completed in 82.06s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0536904335021973s
Received healthy response to inference request in 0.7431952953338623s
Received healthy response to inference request in 1.1077494621276855s
Received healthy response to inference request in 0.8415970802307129s
Received healthy response to inference request in 1.0931107997894287s
5 requests
0 failed requests
5th percentile: 0.7628756523132324
10th percentile: 0.7825560092926025
20th percentile: 0.8219167232513428
30th percentile: 0.891899824142456
40th percentile: 0.9925053119659424
50th percentile: 1.0931107997894287
60th percentile: 1.0989662647247314
70th percentile: 1.1048217296600342
80th percentile: 1.296937656402588
90th percentile: 1.6753140449523927
95th percentile: 1.8645022392272947
99th percentile: 2.0158527946472167
mean time: 1.1678686141967773
Pipeline stage StressChecker completed in 6.76s
meta-llama-meta-llama-3-8b_v8 status is now deployed due to DeploymentManager action
meta-llama-meta-llama-3-8b_v8 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meta-llama-meta-llama-3-8b_v8
Running pipeline stage ISVCDeleter
Checking if service meta-llama-meta-llama-3-8b-v8 is running
Tearing down inference service meta-llama-meta-llama-3-8b-v8
Service meta-llama-meta-llama-3-8b-v8 has been torndown
Pipeline stage ISVCDeleter completed in 4.67s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meta-llama-meta-llama-3-8b-v8/config.json from bucket guanaco-mkml-models
Deleting key meta-llama-meta-llama-3-8b-v8/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meta-llama-meta-llama-3-8b-v8/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meta-llama-meta-llama-3-8b-v8/tokenizer.json from bucket guanaco-mkml-models
Deleting key meta-llama-meta-llama-3-8b-v8/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meta-llama-meta-llama-3-8b-v8_reward/config.json from bucket guanaco-reward-models
Deleting key meta-llama-meta-llama-3-8b-v8_reward/merges.txt from bucket guanaco-reward-models
Deleting key meta-llama-meta-llama-3-8b-v8_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meta-llama-meta-llama-3-8b-v8_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meta-llama-meta-llama-3-8b-v8_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meta-llama-meta-llama-3-8b-v8_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meta-llama-meta-llama-3-8b-v8_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.44s
meta-llama-meta-llama-3-8b_v8 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics