submission_id: zonemercy-vingt-deux-v0-1e5_v15
developer_uid: zonemercy
best_of: 8
celo_rating: 1247.4
display_name: zonemercy-vingt-deux-v0-1e5_v15
family_friendly_score: 0.0
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A6000': 1}
is_internal_developer: True
language_model: zonemercy/Vingt-Deux-v0-1e5
latencies: [{'batch_size': 1, 'throughput': 0.374165382694368, 'latency_mean': 2.6725165116786957, 'latency_p50': 2.6784093379974365, 'latency_p90': 2.9218609809875487}, {'batch_size': 2, 'throughput': 0.5988550059690408, 'latency_mean': 3.3368072056770326, 'latency_p50': 3.356170892715454, 'latency_p90': 3.6728028059005737}, {'batch_size': 3, 'throughput': 0.7557234501364736, 'latency_mean': 3.953821086883545, 'latency_p50': 3.970132350921631, 'latency_p90': 4.368833827972412}, {'batch_size': 4, 'throughput': 0.8782466225664636, 'latency_mean': 4.538488832712173, 'latency_p50': 4.577152848243713, 'latency_p90': 5.0537484884262085}, {'batch_size': 5, 'throughput': 0.9764200657128238, 'latency_mean': 5.097428710460663, 'latency_p50': 5.062581896781921, 'latency_p90': 5.730243873596192}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: zonemercy/Vingt-Deux-v0-
model_name: zonemercy-vingt-deux-v0-1e5_v15
model_num_parameters: 22247282688.0
model_repo: zonemercy/Vingt-Deux-v0-1e5
model_size: 22B
num_battles: 26228
num_wins: 13373
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 0.7
timestamp: 2024-09-23T16:16:59+00:00
us_pacific_date: 2024-09-23
win_ratio: 0.5098749428092115
Download Preference Data
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name zonemercy-vingt-deux-v0-1e5-v15-mkmlizer
Waiting for job on zonemercy-vingt-deux-v0-1e5-v15-mkmlizer to finish
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ _____ __ __ ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ /___/ ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ Version: 0.10.1 ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ https://mk1.ai ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ belonging to: ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ Chai Research Corp. ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ║ ║
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: Downloaded to shared memory in 82.155s
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9ohs3e65, device:0
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: quantized model in 51.884s
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: Processed model zonemercy/Vingt-Deux-v0-1e5 in 134.039s
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v15
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v15/special_tokens_map.json
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v15/config.json
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v15/tokenizer_config.json
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v15/tokenizer.json
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v15/flywheel_model.1.safetensors
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v15/flywheel_model.0.safetensors
zonemercy-vingt-deux-v0-1e5-v15-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 4/507 [00:00<00:13, 37.50it/s] Loading 0: 2%|▏ | 8/507 [00:00<00:17, 27.77it/s] Loading 0: 2%|▏ | 11/507 [00:00<00:18, 27.31it/s] Loading 0: 3%|▎ | 14/507 [00:00<00:22, 22.33it/s] Loading 0: 4%|▎ | 19/507 [00:00<00:16, 28.87it/s] Loading 0: 5%|▍ | 23/507 [00:00<00:18, 26.13it/s] Loading 0: 6%|▌ | 28/507 [00:00<00:15, 30.51it/s] Loading 0: 6%|▋ | 32/507 [00:01<00:17, 27.40it/s] Loading 0: 7%|▋ | 37/507 [00:01<00:14, 31.83it/s] Loading 0: 8%|▊ | 41/507 [00:01<00:16, 28.33it/s] Loading 0: 9%|▉ | 46/507 [00:01<00:14, 32.29it/s] Loading 0: 10%|▉ | 50/507 [00:01<00:15, 28.96it/s] Loading 0: 11%|█ | 54/507 [00:02<00:22, 20.13it/s] Loading 0: 11%|█ | 57/507 [00:02<00:22, 20.09it/s] Loading 0: 12%|█▏ | 61/507 [00:02<00:19, 23.04it/s] Loading 0: 13%|█▎ | 65/507 [00:02<00:19, 22.15it/s] Loading 0: 14%|█▍ | 70/507 [00:02<00:16, 26.88it/s] Loading 0: 15%|█▍ | 75/507 [00:02<00:14, 29.74it/s] Loading 0: 16%|█▌ | 80/507 [00:02<00:14, 30.20it/s] Loading 0: 17%|█▋ | 85/507 [00:03<00:12, 33.04it/s] Loading 0: 18%|█▊ | 89/507 [00:03<00:13, 30.20it/s] Loading 0: 19%|█▊ | 94/507 [00:03<00:12, 34.23it/s] Loading 0: 19%|█▉ | 98/507 [00:03<00:13, 30.22it/s] Loading 0: 20%|██ | 103/507 [00:03<00:11, 34.12it/s] Loading 0: 21%|██ | 107/507 [00:03<00:13, 29.99it/s] Loading 0: 22%|██▏ | 112/507 [00:03<00:11, 33.91it/s] Loading 0: 23%|██▎ | 116/507 [00:04<00:17, 21.90it/s] Loading 0: 24%|██▍ | 122/507 [00:04<00:15, 24.45it/s] Loading 0: 25%|██▌ | 127/507 [00:04<00:13, 27.76it/s] Loading 0: 26%|██▌ | 131/507 [00:04<00:14, 25.18it/s] Loading 0: 27%|██▋ | 136/507 [00:04<00:12, 29.65it/s] Loading 0: 28%|██▊ | 140/507 [00:05<00:13, 27.83it/s] Loading 0: 29%|██▊ | 145/507 [00:05<00:11, 32.00it/s] Loading 0: 29%|██▉ | 149/507 [00:05<00:12, 28.51it/s] Loading 0: 30%|███ | 154/507 [00:05<00:11, 30.92it/s] Loading 0: 31%|███ | 158/507 [00:05<00:12, 28.54it/s] Loading 0: 32%|███▏ | 163/507 [00:05<00:10, 33.05it/s] Loading 0: 33%|███▎ | 168/507 [00:05<00:10, 31.70it/s] Loading 0: 34%|███▍ | 172/507 [00:06<00:16, 20.86it/s] Loading 0: 35%|███▍ | 176/507 [00:06<00:15, 21.66it/s] Loading 0: 36%|███▌ | 181/507 [00:06<00:12, 26.04it/s] Loading 0: 36%|███▋ | 185/507 [00:06<00:12, 25.30it/s] Loading 0: 37%|███▋ | 190/507 [00:06<00:10, 29.34it/s] Loading 0: 38%|███▊ | 194/507 [00:07<00:11, 26.89it/s] Loading 0: 39%|███▉ | 199/507 [00:07<00:10, 30.63it/s] Loading 0: 40%|████ | 203/507 [00:07<00:10, 28.27it/s] Loading 0: 41%|████ | 208/507 [00:07<00:09, 32.62it/s] Loading 0: 42%|████▏ | 212/507 [00:07<00:10, 28.56it/s] Loading 0: 43%|████▎ | 217/507 [00:07<00:08, 33.03it/s] Loading 0: 44%|████▎ | 221/507 [00:07<00:09, 30.55it/s] Loading 0: 44%|████▍ | 225/507 [00:08<00:12, 22.26it/s] Loading 0: 45%|████▌ | 230/507 [00:08<00:11, 24.37it/s] Loading 0: 46%|████▋ | 235/507 [00:08<00:09, 28.62it/s] Loading 0: 47%|████▋ | 239/507 [00:08<00:10, 26.67it/s] Loading 0: 48%|████▊ | 244/507 [00:08<00:08, 31.04it/s] Loading 0: 49%|████▉ | 248/507 [00:08<00:09, 27.62it/s] Loading 0: 50%|████▉ | 253/507 [00:09<00:08, 30.17it/s] Loading 0: 51%|█████ | 257/507 [00:09<00:08, 27.93it/s] Loading 0: 52%|█████▏ | 264/507 [00:09<00:06, 34.78it/s] Loading 0: 53%|█████▎ | 268/507 [00:09<00:07, 32.78it/s] Loading 0: 54%|█████▍ | 273/507 [00:09<00:06, 34.67it/s] Loading 0: 55%|█████▍ | 277/507 [00:09<00:07, 32.29it/s] Loading 0: 55%|█████▌ | 281/507 [00:09<00:06, 32.31it/s] Loading 0: 56%|█████▌ | 285/507 [00:10<00:10, 21.02it/s] Loading 0: 57%|█████▋ | 288/507 [00:10<00:10, 21.26it/s] Loading 0: 58%|█████▊ | 293/507 [00:10<00:09, 22.74it/s] Loading 0: 59%|█████▉ | 298/507 [00:10<00:07, 27.21it/s] Loading 0: 60%|█████▉ | 302/507 [00:27<04:07, 1.21s/it] Loading 0: 61%|██████ | 307/507 [00:27<02:44, 1.22it/s] Loading 0: 61%|██████▏ | 311/507 [00:28<02:00, 1.63it/s] Loading 0: 62%|██████▏ | 316/507 [00:28<01:19, 2.39it/s] Loading 0: 63%|██████▎ | 320/507 [00:28<00:58, 3.17it/s] Loading 0: 64%|██████▍ | 325/507 [00:28<00:39, 4.56it/s] Loading 0: 65%|██████▍ | 329/507 [00:28<00:30, 5.80it/s] Loading 0: 66%|██████▌ | 334/507 [00:28<00:21, 8.10it/s] Loading 0: 67%|██████▋ | 339/507 [00:29<00:15, 10.70it/s] Loading 0: 68%|██████▊ | 343/507 [00:29<00:15, 10.60it/s] Loading 0: 68%|██████▊ | 347/507 [00:29<00:13, 12.10it/s] Loading 0: 69%|██████▉ | 352/507 [00:29<00:09, 15.82it/s] Loading 0: 70%|███████ | 356/507 [00:29<00:08, 17.07it/s] Loading 0: 71%|███████ | 361/507 [00:30<00:07, 20.79it/s] Loading 0: 72%|███████▏ | 365/507 [00:30<00:06, 20.57it/s] Loading 0: 73%|███████▎ | 370/507 [00:30<00:05, 24.80it/s] Loading 0: 74%|███████▍ | 374/507 [00:30<00:05, 24.08it/s] Loading 0: 75%|███████▍ | 379/507 [00:30<00:04, 28.18it/s] Loading 0: 76%|███████▌ | 383/507 [00:30<00:04, 25.28it/s] Loading 0: 77%|███████▋ | 388/507 [00:31<00:04, 29.04it/s] Loading 0: 77%|███████▋ | 392/507 [00:31<00:04, 27.08it/s] Loading 0: 78%|███████▊ | 396/507 [00:31<00:05, 19.64it/s] Loading 0: 79%|███████▉ | 401/507 [00:31<00:04, 21.50it/s] Loading 0: 80%|████████ | 406/507 [00:31<00:03, 25.29it/s] Loading 0: 81%|████████ | 410/507 [00:32<00:04, 23.79it/s] Loading 0: 82%|████████▏ | 415/507 [00:32<00:03, 26.97it/s] Loading 0: 83%|████████▎ | 419/507 [00:32<00:03, 25.01it/s] Loading 0: 84%|████████▎ | 424/507 [00:32<00:02, 28.90it/s] Loading 0: 84%|████████▍ | 428/507 [00:32<00:02, 26.41it/s] Loading 0: 85%|████████▌ | 433/507 [00:32<00:02, 30.66it/s] Loading 0: 86%|████████▌ | 437/507 [00:32<00:02, 28.40it/s] Loading 0: 88%|████████▊ | 444/507 [00:33<00:01, 35.05it/s] Loading 0: 88%|████████▊ | 448/507 [00:33<00:01, 33.34it/s] Loading 0: 89%|████████▉ | 452/507 [00:33<00:01, 34.30it/s] Loading 0: 90%|████████▉ | 456/507 [00:35<00:10, 5.00it/s] Loading 0: 91%|█████████ | 459/507 [00:36<00:08, 5.91it/s] Loading 0: 92%|█████████▏| 465/507 [00:36<00:04, 8.56it/s] Loading 0: 93%|█████████▎| 470/507 [00:36<00:03, 11.41it/s] Loading 0: 93%|█████████▎| 474/507 [00:36<00:02, 12.81it/s] Loading 0: 94%|█████████▍| 479/507 [00:36<00:01, 16.49it/s] Loading 0: 95%|█████████▌| 483/507 [00:36<00:01, 17.68it/s] Loading 0: 96%|█████████▋| 488/507 [00:37<00:00, 21.59it/s] Loading 0: 97%|█████████▋| 492/507 [00:37<00:00, 21.27it/s] Loading 0: 98%|█████████▊| 497/507 [00:37<00:00, 25.51it/s] Loading 0: 99%|█████████▉| 501/507 [00:37<00:00, 24.78it/s] Loading 0: 100%|█████████▉| 506/507 [00:37<00:00, 29.18it/s]
Job zonemercy-vingt-deux-v0-1e5-v15-mkmlizer completed after 178.67s with status: succeeded
Stopping job with name zonemercy-vingt-deux-v0-1e5-v15-mkmlizer
Pipeline stage MKMLizer completed in 179.68s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-vingt-deux-v0-1e5-v15
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v15 to be ready
Failed to get response for submission cycy233-nemo-p-e-v1-c1_v1: ('http://cycy233-nemo-p-e-v1-c1-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:40170->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_masal_2024-09-19: ('http://chaiml-elo-alignment-run-3-v44-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service zonemercy-vingt-deux-v0-1e5-v15 ready after 181.04120302200317s
Pipeline stage MKMLDeployer completed in 181.41s
run pipeline stage %s
Running pipeline stage StressChecker
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 3.3884990215301514s
Received healthy response to inference request in 2.9578769207000732s
Received healthy response to inference request in 3.6923487186431885s
Received healthy response to inference request in 2.6064352989196777s
Received healthy response to inference request in 2.444013833999634s
5 requests
0 failed requests
5th percentile: 2.4764981269836426
10th percentile: 2.5089824199676514
20th percentile: 2.573951005935669
30th percentile: 2.6767236232757567
40th percentile: 2.817300271987915
50th percentile: 2.9578769207000732
60th percentile: 3.1301257610321045
70th percentile: 3.3023746013641357
80th percentile: 3.4492689609527587
90th percentile: 3.570808839797974
95th percentile: 3.631578779220581
99th percentile: 3.680194730758667
mean time: 3.017834758758545
Pipeline stage StressChecker completed in 15.93s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.82s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v15 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-vingt-deux-v0-1e5-v15-profiler
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v15-profiler to be ready
Inference service zonemercy-vingt-deux-v0-1e5-v15-profiler ready after 180.42382955551147s
Pipeline stage MKMLProfilerDeployer completed in 180.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deuxfc0ff4a263b9f634e2b503b5423306f0-deplo68mjp:/code/chaiverse_profiler_1727108828 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deuxfc0ff4a263b9f634e2b503b5423306f0-deplo68mjp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727108828 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1727108828/summary.json'
kubectl exec -it zonemercy-vingt-deuxfc0ff4a263b9f634e2b503b5423306f0-deplo68mjp --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727108828/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1570.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-v0-1e5-v15-profiler is running
Tearing down inference service zonemercy-vingt-deux-v0-1e5-v15-profiler
Service zonemercy-vingt-deux-v0-1e5-v15-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.02s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v15 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-small_5341_v26 status is now torndown due to DeploymentManager action
Deleting key zonemercy-vingt-deux-v0-1e5-v16/tokenizer.json from bucket guanaco-mkml-models
zonemercy-vingt-deux-v0-1e5_v15 status is now torndown due to DeploymentManager action