submission_id: google-gemma-2-27b-it_v4
developer_uid: Jellywibble
alignment_samples: 4144
alignment_score: 3.464250534210216
best_of: 4
celo_rating: 1180.05
display_name: google-gemma-2-27b-it_v1
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}
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: 119196
num_wins: 56526
propriety_score: 0.7407802795031055
propriety_total_count: 10304.0
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: 2024-07-14T00:40:53+00:00
us_pacific_date: 2024-07-13
win_ratio: 0.47422732306453236
Resubmit model
Running pipeline stage MKMLizer
Starting job with name google-gemma-2-27b-it-v4-mkmlizer
Waiting for job on google-gemma-2-27b-it-v4-mkmlizer to finish
google-gemma-2-27b-it-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
google-gemma-2-27b-it-v4-mkmlizer: ║ _____ __ __ ║
google-gemma-2-27b-it-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
google-gemma-2-27b-it-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
google-gemma-2-27b-it-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
google-gemma-2-27b-it-v4-mkmlizer: ║ /___/ ║
google-gemma-2-27b-it-v4-mkmlizer: ║ ║
google-gemma-2-27b-it-v4-mkmlizer: ║ Version: 0.9.5.post2 ║
google-gemma-2-27b-it-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
google-gemma-2-27b-it-v4-mkmlizer: ║ https://mk1.ai ║
google-gemma-2-27b-it-v4-mkmlizer: ║ ║
google-gemma-2-27b-it-v4-mkmlizer: ║ The license key for the current software has been verified as ║
google-gemma-2-27b-it-v4-mkmlizer: ║ belonging to: ║
google-gemma-2-27b-it-v4-mkmlizer: ║ ║
google-gemma-2-27b-it-v4-mkmlizer: ║ Chai Research Corp. ║
google-gemma-2-27b-it-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
google-gemma-2-27b-it-v4-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
google-gemma-2-27b-it-v4-mkmlizer: ║ ║
google-gemma-2-27b-it-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
google-gemma-2-27b-it-v4-mkmlizer: Downloaded to shared memory in 81.875s
google-gemma-2-27b-it-v4-mkmlizer: quantizing model to /dev/shm/model_cache
google-gemma-2-27b-it-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
google-gemma-2-27b-it-v4-mkmlizer: quantized model in 88.405s
google-gemma-2-27b-it-v4-mkmlizer: Processed model google/gemma-2-27b-it in 170.281s
google-gemma-2-27b-it-v4-mkmlizer: creating bucket guanaco-mkml-models
google-gemma-2-27b-it-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
google-gemma-2-27b-it-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/google-gemma-2-27b-it-v4
google-gemma-2-27b-it-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/google-gemma-2-27b-it-v4/config.json
google-gemma-2-27b-it-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/google-gemma-2-27b-it-v4/special_tokens_map.json
google-gemma-2-27b-it-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/google-gemma-2-27b-it-v4/tokenizer_config.json
google-gemma-2-27b-it-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/google-gemma-2-27b-it-v4/tokenizer.model
google-gemma-2-27b-it-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/google-gemma-2-27b-it-v4/tokenizer.json
google-gemma-2-27b-it-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/google-gemma-2-27b-it-v4/flywheel_model.2.safetensors
google-gemma-2-27b-it-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/google-gemma-2-27b-it-v4/flywheel_model.0.safetensors
google-gemma-2-27b-it-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/google-gemma-2-27b-it-v4/flywheel_model.1.safetensors
google-gemma-2-27b-it-v4-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
google-gemma-2-27b-it-v4-mkmlizer: Loading 0: 0%| | 0/508 [00:00<?, ?it/s] Loading 0: 1%| | 4/508 [00:00<00:13, 36.03it/s] Loading 0: 3%|▎ | 14/508 [00:00<00:08, 61.19it/s] Loading 0: 4%|▍ | 20/508 [00:00<00:08, 57.92it/s] Loading 0: 6%|▌ | 28/508 [00:00<00:15, 31.51it/s] Loading 0: 6%|▋ | 33/508 [00:00<00:15, 31.57it/s] Loading 0: 7%|▋ | 37/508 [00:01<00:14, 33.11it/s] Loading 0: 9%|▉ | 47/508 [00:01<00:10, 45.43it/s] Loading 0: 10%|█ | 53/508 [00:01<00:09, 47.29it/s] Loading 0: 12%|█▏ | 59/508 [00:01<00:09, 48.25it/s] Loading 0: 13%|█▎ | 68/508 [00:01<00:07, 55.33it/s] Loading 0: 15%|█▍ | 74/508 [00:01<00:15, 28.69it/s] Loading 0: 16%|█▌ | 81/508 [00:02<00:12, 33.80it/s] Loading 0: 17%|█▋ | 87/508 [00:02<00:11, 38.05it/s] Loading 0: 19%|█▉ | 97/508 [00:02<00:08, 47.69it/s] Loading 0: 20%|██ | 103/508 [00:02<00:08, 48.71it/s] Loading 0: 21%|██▏ | 109/508 [00:02<00:08, 48.30it/s] Loading 0: 23%|██▎ | 118/508 [00:03<00:12, 32.40it/s] Loading 0: 24%|██▍ | 124/508 [00:03<00:10, 36.48it/s] Loading 0: 25%|██▌ | 129/508 [00:03<00:09, 38.42it/s] Loading 0: 27%|██▋ | 136/508 [00:03<00:08, 42.71it/s] Loading 0: 29%|██▊ | 146/508 [00:03<00:06, 52.40it/s] Loading 0: 30%|██▉ | 152/508 [00:03<00:06, 52.76it/s] Loading 0: 31%|███ | 158/508 [00:03<00:06, 51.41it/s] Loading 0: 34%|███▎ | 171/508 [00:04<00:09, 37.26it/s] Loading 0: 35%|███▍ | 176/508 [00:04<00:09, 35.67it/s] Loading 0: 36%|███▌ | 181/508 [00:04<00:09, 34.82it/s] Loading 0: 38%|███▊ | 191/508 [00:04<00:07, 44.63it/s] Loading 0: 38%|███▊ | 191/508 [00:20<00:07, 44.63it/s] Loading 0: 38%|███▊ | 192/508 [00:28<06:37, 1.26s/it] Loading 0: 40%|███▉ | 202/508 [00:28<03:41, 1.38it/s] Loading 0: 42%|████▏ | 211/508 [00:28<02:20, 2.12it/s] Loading 0: 43%|████▎ | 218/508 [00:28<01:44, 2.79it/s] Loading 0: 44%|████▍ | 224/508 [00:29<01:16, 3.69it/s] Loading 0: 46%|████▌ | 234/508 [00:29<00:47, 5.79it/s] Loading 0: 47%|████▋ | 240/508 [00:29<00:36, 7.41it/s] Loading 0: 48%|████▊ | 246/508 [00:29<00:27, 9.50it/s] Loading 0: 50%|█████ | 255/508 [00:29<00:18, 13.76it/s] Loading 0: 51%|█████▏ | 261/508 [00:30<00:17, 13.73it/s] Loading 0: 53%|█████▎ | 267/508 [00:30<00:14, 17.16it/s] Loading 0: 54%|█████▎ | 272/508 [00:30<00:11, 20.14it/s] Loading 0: 55%|█████▍ | 279/508 [00:30<00:08, 25.48it/s] Loading 0: 57%|█████▋ | 289/508 [00:30<00:06, 34.78it/s] Loading 0: 58%|█████▊ | 295/508 [00:30<00:05, 38.18it/s] Loading 0: 59%|█████▉ | 301/508 [00:30<00:05, 40.78it/s] Loading 0: 62%|██████▏ | 314/508 [00:31<00:05, 33.75it/s] Loading 0: 63%|██████▎ | 319/508 [00:31<00:05, 33.33it/s] Loading 0: 64%|██████▍ | 324/508 [00:31<00:05, 33.08it/s] Loading 0: 66%|██████▌ | 334/508 [00:31<00:04, 42.85it/s] Loading 0: 68%|██████▊ | 344/508 [00:31<00:03, 51.27it/s] Loading 0: 69%|██████▉ | 350/508 [00:31<00:03, 51.80it/s] Loading 0: 71%|███████ | 359/508 [00:32<00:04, 34.43it/s] Loading 0: 72%|███████▏ | 364/508 [00:32<00:03, 36.52it/s] Loading 0: 73%|███████▎ | 369/508 [00:32<00:03, 35.35it/s] Loading 0: 74%|███████▍ | 378/508 [00:32<00:02, 43.85it/s] Loading 0: 76%|███████▋ | 388/508 [00:32<00:02, 52.34it/s] Loading 0: 78%|███████▊ | 394/508 [00:32<00:02, 51.86it/s] Loading 0: 79%|███████▊ | 400/508 [00:33<00:02, 50.43it/s] Loading 0: 80%|███████▉ | 406/508 [00:33<00:03, 29.56it/s] Loading 0: 81%|████████ | 411/508 [00:33<00:02, 32.61it/s] Loading 0: 83%|████████▎ | 421/508 [00:33<00:02, 43.08it/s] Loading 0: 84%|████████▍ | 427/508 [00:33<00:01, 45.60it/s] Loading 0: 85%|████████▌ | 433/508 [00:33<00:01, 46.82it/s] Loading 0: 87%|████████▋ | 443/508 [00:34<00:01, 55.84it/s] Loading 0: 89%|████████▊ | 450/508 [00:34<00:01, 57.24it/s] Loading 0: 89%|████████▉ | 451/508 [00:55<00:00, 57.24it/s] Loading 0: 89%|████████▉ | 452/508 [00:55<01:02, 1.11s/it] Loading 0: 90%|████████▉ | 457/508 [00:55<00:42, 1.20it/s] Loading 0: 91%|█████████ | 462/508 [00:55<00:28, 1.64it/s] Loading 0: 92%|█████████▏| 467/508 [00:56<00:18, 2.24it/s] Loading 0: 94%|█████████▍| 477/508 [00:56<00:07, 3.97it/s] Loading 0: 96%|█████████▌| 487/508 [00:56<00:03, 6.31it/s] Loading 0: 97%|█████████▋| 493/508 [00:56<00:01, 8.11it/s] Loading 0: 99%|█████████▉| 502/508 [00:56<00:00, 10.25it/s] Loading 0: 100%|█████████▉| 507/508 [00:57<00:00, 12.35it/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-v4-mkmlizer: warnings.warn(
google-gemma-2-27b-it-v4-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-v4-mkmlizer: warnings.warn(
google-gemma-2-27b-it-v4-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-v4-mkmlizer: warnings.warn(
google-gemma-2-27b-it-v4-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.51s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.54s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.99s/it]
google-gemma-2-27b-it-v4-mkmlizer: Saving duration: 2.479s
google-gemma-2-27b-it-v4-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 15.304s
google-gemma-2-27b-it-v4-mkmlizer: creating bucket guanaco-reward-models
google-gemma-2-27b-it-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
google-gemma-2-27b-it-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/google-gemma-2-27b-it-v4_reward
google-gemma-2-27b-it-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/google-gemma-2-27b-it-v4_reward/special_tokens_map.json
google-gemma-2-27b-it-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/google-gemma-2-27b-it-v4_reward/merges.txt
google-gemma-2-27b-it-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/google-gemma-2-27b-it-v4_reward/tokenizer_config.json
google-gemma-2-27b-it-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/google-gemma-2-27b-it-v4_reward/config.json
google-gemma-2-27b-it-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/google-gemma-2-27b-it-v4_reward/vocab.json
google-gemma-2-27b-it-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/google-gemma-2-27b-it-v4_reward/tokenizer.json
google-gemma-2-27b-it-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/google-gemma-2-27b-it-v4_reward/reward.tensors
Job google-gemma-2-27b-it-v4-mkmlizer completed after 225.97s with status: succeeded
Stopping job with name google-gemma-2-27b-it-v4-mkmlizer
Pipeline stage MKMLizer completed in 226.80s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 1.31s
Running pipeline stage ISVCDeployer
Creating inference service google-gemma-2-27b-it-v4
Waiting for inference service google-gemma-2-27b-it-v4 to be ready
Inference service google-gemma-2-27b-it-v4 ready after 70.33524012565613s
Pipeline stage ISVCDeployer completed in 77.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.8378801345825195s
Received healthy response to inference request in 2.6602468490600586s
Received healthy response to inference request in 2.934095621109009s
Received healthy response to inference request in 2.3809974193573s
Received healthy response to inference request in 2.44647216796875s
5 requests
0 failed requests
5th percentile: 2.3940923690795897
10th percentile: 2.40718731880188
20th percentile: 2.43337721824646
30th percentile: 2.4892271041870115
40th percentile: 2.574736976623535
50th percentile: 2.6602468490600586
60th percentile: 2.7697863578796387
70th percentile: 2.8793258666992188
80th percentile: 3.114852523803711
90th percentile: 3.4763663291931155
95th percentile: 3.6571232318878173
99th percentile: 3.801728754043579
mean time: 2.8519384384155275
Pipeline stage StressChecker completed in 14.83s
google-gemma-2-27b-it_v4 status is now deployed due to DeploymentManager action
google-gemma-2-27b-it_v4 status is now inactive due to auto deactivation removed underperforming models
google-gemma-2-27b-it_v4 status is now deployed due to admin request
admin requested tearing down of google-gemma-2-27b-it_v4
Running pipeline stage ISVCDeleter
Checking if service google-gemma-2-27b-it-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.96s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key google-gemma-2-27b-it-v4/config.json from bucket guanaco-mkml-models
Deleting key google-gemma-2-27b-it-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key google-gemma-2-27b-it-v4/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key google-gemma-2-27b-it-v4/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key google-gemma-2-27b-it-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key google-gemma-2-27b-it-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key google-gemma-2-27b-it-v4/tokenizer.model from bucket guanaco-mkml-models
Deleting key google-gemma-2-27b-it-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key google-gemma-2-27b-it-v4_reward/config.json from bucket guanaco-reward-models
Deleting key google-gemma-2-27b-it-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key google-gemma-2-27b-it-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key google-gemma-2-27b-it-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key google-gemma-2-27b-it-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key google-gemma-2-27b-it-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key google-gemma-2-27b-it-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 8.63s
google-gemma-2-27b-it_v4 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics