submission_id: google-gemma-2-27b-it_v5
developer_uid: Jellywibble
alignment_samples: 0
best_of: 4
celo_rating: 1161.59
display_name: google-gemma-2-27b-it_v1
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': 1.2, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<end_of_turn>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
is_internal_developer: True
language_model: google/gemma-2-27b-it
max_input_tokens: 512
max_output_tokens: 64
model_architecture: Gemma2ForCausalLM
model_group: google/gemma-2-27b-it
model_name: google-gemma-2-27b-it_v1
model_num_parameters: 28731935232.0
model_repo: google/gemma-2-27b-it
model_size: 29B
num_battles: 114892
num_wins: 51505
propriety_score: 0.7393987656778818
propriety_total_count: 10046.0
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_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-14T00:41:16+00:00
us_pacific_date: 2024-07-13
win_ratio: 0.4482905685339275
Resubmit model
Running pipeline stage MKMLizer
Starting job with name google-gemma-2-27b-it-v5-mkmlizer
Waiting for job on google-gemma-2-27b-it-v5-mkmlizer to finish
google-gemma-2-27b-it-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
google-gemma-2-27b-it-v5-mkmlizer: ║ _____ __ __ ║
google-gemma-2-27b-it-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
google-gemma-2-27b-it-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
google-gemma-2-27b-it-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
google-gemma-2-27b-it-v5-mkmlizer: ║ /___/ ║
google-gemma-2-27b-it-v5-mkmlizer: ║ ║
google-gemma-2-27b-it-v5-mkmlizer: ║ Version: 0.9.5.post2 ║
google-gemma-2-27b-it-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
google-gemma-2-27b-it-v5-mkmlizer: ║ https://mk1.ai ║
google-gemma-2-27b-it-v5-mkmlizer: ║ ║
google-gemma-2-27b-it-v5-mkmlizer: ║ The license key for the current software has been verified as ║
google-gemma-2-27b-it-v5-mkmlizer: ║ belonging to: ║
google-gemma-2-27b-it-v5-mkmlizer: ║ ║
google-gemma-2-27b-it-v5-mkmlizer: ║ Chai Research Corp. ║
google-gemma-2-27b-it-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
google-gemma-2-27b-it-v5-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
google-gemma-2-27b-it-v5-mkmlizer: ║ ║
google-gemma-2-27b-it-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
google-gemma-2-27b-it-v5-mkmlizer: Downloaded to shared memory in 84.185s
google-gemma-2-27b-it-v5-mkmlizer: quantizing model to /dev/shm/model_cache
google-gemma-2-27b-it-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
google-gemma-2-27b-it-v5-mkmlizer: quantized model in 88.056s
google-gemma-2-27b-it-v5-mkmlizer: Processed model google/gemma-2-27b-it in 172.241s
google-gemma-2-27b-it-v5-mkmlizer: creating bucket guanaco-mkml-models
google-gemma-2-27b-it-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
google-gemma-2-27b-it-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/google-gemma-2-27b-it-v5
google-gemma-2-27b-it-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/google-gemma-2-27b-it-v5/config.json
google-gemma-2-27b-it-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/google-gemma-2-27b-it-v5/tokenizer_config.json
google-gemma-2-27b-it-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/google-gemma-2-27b-it-v5/special_tokens_map.json
google-gemma-2-27b-it-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/google-gemma-2-27b-it-v5/tokenizer.model
google-gemma-2-27b-it-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/google-gemma-2-27b-it-v5/tokenizer.json
google-gemma-2-27b-it-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/google-gemma-2-27b-it-v5/flywheel_model.2.safetensors
google-gemma-2-27b-it-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/google-gemma-2-27b-it-v5/flywheel_model.0.safetensors
google-gemma-2-27b-it-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/google-gemma-2-27b-it-v5/flywheel_model.1.safetensors
google-gemma-2-27b-it-v5-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
google-gemma-2-27b-it-v5-mkmlizer: Loading 0: 0%| | 0/508 [00:00<?, ?it/s] Loading 0: 1%| | 4/508 [00:00<00:13, 37.00it/s] Loading 0: 3%|▎ | 14/508 [00:00<00:07, 62.27it/s] Loading 0: 4%|▍ | 21/508 [00:00<00:08, 60.62it/s] Loading 0: 6%|▌ | 28/508 [00:00<00:15, 31.28it/s] Loading 0: 6%|▋ | 33/508 [00:00<00:15, 31.34it/s] Loading 0: 7%|▋ | 37/508 [00:01<00:14, 32.97it/s] Loading 0: 9%|▉ | 47/508 [00:01<00:10, 45.61it/s] Loading 0: 10%|█ | 53/508 [00:01<00:09, 47.89it/s] Loading 0: 12%|█▏ | 59/508 [00:01<00:09, 48.56it/s] Loading 0: 13%|█▎ | 68/508 [00:01<00:07, 55.70it/s] Loading 0: 15%|█▍ | 74/508 [00:01<00:15, 27.97it/s] Loading 0: 16%|█▌ | 81/508 [00:02<00:12, 33.14it/s] Loading 0: 17%|█▋ | 87/508 [00:02<00:11, 37.43it/s] Loading 0: 19%|█▉ | 97/508 [00:02<00:08, 47.42it/s] Loading 0: 20%|██ | 103/508 [00:02<00:08, 48.92it/s] Loading 0: 21%|██▏ | 109/508 [00:02<00:08, 49.07it/s] Loading 0: 23%|██▎ | 118/508 [00:03<00:11, 32.82it/s] Loading 0: 24%|██▍ | 124/508 [00:03<00:10, 36.69it/s] Loading 0: 25%|██▌ | 129/508 [00:03<00:09, 38.52it/s] Loading 0: 27%|██▋ | 136/508 [00:03<00:08, 42.95it/s] Loading 0: 29%|██▊ | 146/508 [00:03<00:06, 52.52it/s] Loading 0: 30%|██▉ | 152/508 [00:03<00:06, 52.94it/s] Loading 0: 31%|███ | 158/508 [00:03<00:06, 51.95it/s] Loading 0: 34%|███▎ | 171/508 [00:04<00:08, 38.03it/s] Loading 0: 35%|███▍ | 176/508 [00:04<00:09, 36.51it/s] Loading 0: 36%|███▌ | 181/508 [00:04<00:09, 34.31it/s] Loading 0: 38%|███▊ | 191/508 [00:04<00:07, 44.21it/s] Loading 0: 38%|███▊ | 191/508 [00:25<00:07, 44.21it/s] Loading 0: 38%|███▊ | 192/508 [00:25<05:58, 1.13s/it] Loading 0: 40%|███▉ | 202/508 [00:25<03:20, 1.53it/s] Loading 0: 42%|████▏ | 211/508 [00:26<02:06, 2.34it/s] Loading 0: 43%|████▎ | 218/508 [00:26<01:35, 3.04it/s] Loading 0: 44%|████▍ | 224/508 [00:26<01:10, 4.02it/s] Loading 0: 46%|████▌ | 234/508 [00:26<00:43, 6.28it/s] Loading 0: 47%|████▋ | 240/508 [00:27<00:33, 8.03it/s] Loading 0: 48%|████▊ | 246/508 [00:27<00:25, 10.28it/s] Loading 0: 50%|█████ | 255/508 [00:27<00:17, 14.82it/s] Loading 0: 52%|█████▏ | 262/508 [00:27<00:16, 14.80it/s] Loading 0: 53%|█████▎ | 268/508 [00:27<00:13, 18.31it/s] Loading 0: 55%|█████▍ | 278/508 [00:27<00:08, 25.96it/s] Loading 0: 56%|█████▌ | 284/508 [00:28<00:07, 29.79it/s] Loading 0: 57%|█████▋ | 290/508 [00:28<00:06, 33.16it/s] Loading 0: 59%|█████▉ | 300/508 [00:28<00:04, 42.72it/s] Loading 0: 60%|██████ | 307/508 [00:28<00:04, 46.49it/s] Loading 0: 62%|██████▏ | 314/508 [00:28<00:06, 32.09it/s] Loading 0: 63%|██████▎ | 319/508 [00:28<00:05, 32.06it/s] Loading 0: 64%|██████▍ | 324/508 [00:29<00:05, 32.18it/s] Loading 0: 66%|██████▌ | 334/508 [00:29<00:04, 42.64it/s] Loading 0: 68%|██████▊ | 344/508 [00:29<00:03, 51.55it/s] Loading 0: 69%|██████▉ | 351/508 [00:29<00:02, 53.54it/s] Loading 0: 71%|███████ | 359/508 [00:29<00:04, 33.87it/s] Loading 0: 72%|███████▏ | 364/508 [00:30<00:03, 36.11it/s] Loading 0: 73%|███████▎ | 369/508 [00:30<00:04, 34.28it/s] Loading 0: 74%|███████▍ | 378/508 [00:30<00:03, 41.57it/s] Loading 0: 76%|███████▋ | 388/508 [00:30<00:02, 50.93it/s] Loading 0: 78%|███████▊ | 394/508 [00:30<00:02, 51.88it/s] Loading 0: 79%|███████▊ | 400/508 [00:30<00:02, 51.13it/s] Loading 0: 80%|███████▉ | 406/508 [00:31<00:03, 30.63it/s] Loading 0: 81%|████████ | 411/508 [00:31<00:02, 33.62it/s] Loading 0: 83%|████████▎ | 421/508 [00:31<00:01, 44.19it/s] Loading 0: 84%|████████▍ | 427/508 [00:31<00:01, 46.16it/s] Loading 0: 85%|████████▌ | 433/508 [00:31<00:01, 46.82it/s] Loading 0: 87%|████████▋ | 443/508 [00:31<00:01, 53.35it/s] Loading 0: 88%|████████▊ | 449/508 [00:31<00:01, 48.77it/s] Loading 0: 89%|████████▉ | 451/508 [00:52<00:01, 48.77it/s] Loading 0: 89%|████████▉ | 452/508 [00:52<01:00, 1.08s/it] Loading 0: 90%|████████▉ | 457/508 [00:53<00:41, 1.22it/s] Loading 0: 91%|█████████ | 461/508 [00:53<00:29, 1.57it/s] Loading 0: 92%|█████████▏| 466/508 [00:53<00:19, 2.19it/s] Loading 0: 94%|█████████▎| 476/508 [00:53<00:08, 3.94it/s] Loading 0: 95%|█████████▍| 482/508 [00:53<00:04, 5.33it/s] Loading 0: 96%|█████████▌| 488/508 [00:53<00:02, 7.17it/s] Loading 0: 98%|█████████▊| 497/508 [00:54<00:01, 10.92it/s] Loading 0: 99%|█████████▉| 503/508 [00:54<00:00, 11.71it/s] /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.
google-gemma-2-27b-it-v5-mkmlizer: warnings.warn(
google-gemma-2-27b-it-v5-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.
google-gemma-2-27b-it-v5-mkmlizer: warnings.warn(
google-gemma-2-27b-it-v5-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.
google-gemma-2-27b-it-v5-mkmlizer: warnings.warn(
google-gemma-2-27b-it-v5-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.83s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.95s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.38s/it]
google-gemma-2-27b-it-v5-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:01<00:01, 1.53s/it] Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00, 1.32it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00, 1.15it/s]
google-gemma-2-27b-it-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
google-gemma-2-27b-it-v5-mkmlizer: Saving duration: 2.260s
google-gemma-2-27b-it-v5-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 15.583s
google-gemma-2-27b-it-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
google-gemma-2-27b-it-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/google-gemma-2-27b-it-v5_reward
google-gemma-2-27b-it-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/google-gemma-2-27b-it-v5_reward/config.json
google-gemma-2-27b-it-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/google-gemma-2-27b-it-v5_reward/special_tokens_map.json
google-gemma-2-27b-it-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/google-gemma-2-27b-it-v5_reward/tokenizer_config.json
google-gemma-2-27b-it-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/google-gemma-2-27b-it-v5_reward/merges.txt
google-gemma-2-27b-it-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/google-gemma-2-27b-it-v5_reward/vocab.json
google-gemma-2-27b-it-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/google-gemma-2-27b-it-v5_reward/tokenizer.json
google-gemma-2-27b-it-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/google-gemma-2-27b-it-v5_reward/reward.tensors
Job google-gemma-2-27b-it-v5-mkmlizer completed after 226.13s with status: succeeded
Stopping job with name google-gemma-2-27b-it-v5-mkmlizer
Pipeline stage MKMLizer completed in 226.80s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.07s
Running pipeline stage ISVCDeployer
Creating inference service google-gemma-2-27b-it-v5
Waiting for inference service google-gemma-2-27b-it-v5 to be ready
Inference service google-gemma-2-27b-it-v5 ready after 60.30229043960571s
Pipeline stage ISVCDeployer completed in 67.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.259756326675415s
Received healthy response to inference request in 2.071767568588257s
Received healthy response to inference request in 2.6287059783935547s
Received healthy response to inference request in 3.14523983001709s
Received healthy response to inference request in 1.5343537330627441s
5 requests
0 failed requests
5th percentile: 1.6418365001678468
10th percentile: 1.7493192672729492
20th percentile: 1.9642848014831542
30th percentile: 2.1831552505493166
40th percentile: 2.4059306144714356
50th percentile: 2.6287059783935547
60th percentile: 2.8353195190429688
70th percentile: 3.041933059692383
80th percentile: 3.168143129348755
90th percentile: 3.213949728012085
95th percentile: 3.23685302734375
99th percentile: 3.255175666809082
mean time: 2.527964687347412
Pipeline stage StressChecker completed in 13.20s
google-gemma-2-27b-it_v5 status is now deployed due to DeploymentManager action
google-gemma-2-27b-it_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of google-gemma-2-27b-it_v5
Running pipeline stage ISVCDeleter
Checking if service google-gemma-2-27b-it-v5 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.06s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key google-gemma-2-27b-it-v5/config.json from bucket guanaco-mkml-models
Deleting key google-gemma-2-27b-it-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key google-gemma-2-27b-it-v5/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key google-gemma-2-27b-it-v5/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key google-gemma-2-27b-it-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key google-gemma-2-27b-it-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key google-gemma-2-27b-it-v5/tokenizer.model from bucket guanaco-mkml-models
Deleting key google-gemma-2-27b-it-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key google-gemma-2-27b-it-v5_reward/config.json from bucket guanaco-reward-models
Deleting key google-gemma-2-27b-it-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key google-gemma-2-27b-it-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key google-gemma-2-27b-it-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key google-gemma-2-27b-it-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key google-gemma-2-27b-it-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key google-gemma-2-27b-it-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 8.66s
google-gemma-2-27b-it_v5 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics