chaiml-nemo-20241014-mer_7710

developer_uid: azuruce
submission_id: chaiml-nemo-20241014-mer_7710_v2
model_name: 1014-merge-v1-vicuna
model_group: ChaiML/nemo-20241014_mer
status: torndown
timestamp: 2024-10-15T15:12:46+00:00
num_battles: 6608
num_wins: 3727
celo_rating: 1282.88
family_friendly_score: 0.5650121964153144
family_friendly_standard_error: 0.006232206157113202
submission_type: basic
model_repo: ChaiML/nemo-20241014_merge_v1-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: 1014-merge-v1-vicuna
is_internal_developer: True
language_model: ChaiML/nemo-20241014_merge_v1-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-15
win_ratio: 0.5640133171912833
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', '<|eot_id|>', '<|end_of_text|>', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '### Instruction:\n{memory}\n', 'prompt_template': '### Input:\n{prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:', 'truncate_by_message': False}
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 chaiml-nemo-20241014-mer-7710-v2-mkmlizer
Waiting for job on chaiml-nemo-20241014-mer-7710-v2-mkmlizer to finish
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: Downloaded to shared memory in 34.582s
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9rlsjpbd, device:0
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: quantized model in 37.068s
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: Processed model ChaiML/nemo-20241014_merge_v1-albert in 71.650s
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-7710-v2
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-7710-v2/config.json
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-7710-v2/special_tokens_map.json
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-7710-v2/tokenizer_config.json
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-7710-v2/tokenizer.json
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241014-mer-7710-v2/flywheel_model.0.safetensors
chaiml-nemo-20241014-mer-7710-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:35,  3.09s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:58,  1.19it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:11,  2.68it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:23,  4.18it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:40,  8.30it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:28, 11.66it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:22, 14.90it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.54it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 18.93it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 24.08it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:11, 26.50it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:10, 29.86it/s]
Loading 0:  17%|█▋        | 63/363 [00:07<00:09, 31.86it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:09, 32.35it/s]
Loading 0:  20%|█▉        | 71/363 [00:08<00:08, 33.68it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:07, 38.87it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:06, 40.31it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:08, 34.49it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 42.93it/s]
Loading 0:  28%|██▊       | 101/363 [00:08<00:06, 42.77it/s]
Loading 0:  29%|██▉       | 106/363 [00:08<00:06, 42.00it/s]
Loading 0:  31%|███       | 113/363 [00:09<00:05, 46.47it/s]
Loading 0:  33%|███▎      | 118/363 [00:09<00:05, 46.29it/s]
Loading 0:  34%|███▍      | 123/363 [00:09<00:08, 26.79it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 35.16it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:06, 36.97it/s]
Loading 0:  39%|███▉      | 142/363 [00:09<00:05, 37.32it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:05, 42.75it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:04, 43.88it/s]
Loading 0:  44%|████▍     | 159/363 [00:10<00:05, 37.17it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:04, 44.14it/s]
Loading 0:  47%|████▋     | 171/363 [00:10<00:04, 42.21it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:04, 42.16it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:04, 41.37it/s]
Loading 0:  52%|█████▏    | 187/363 [00:10<00:04, 40.37it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:03, 45.06it/s]
Loading 0:  55%|█████▍    | 198/363 [00:11<00:03, 44.62it/s]
Loading 0:  56%|█████▌    | 203/363 [00:11<00:05, 31.24it/s]
Loading 0:  57%|█████▋    | 207/363 [00:11<00:04, 33.00it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:04, 36.10it/s]
Loading 0:  60%|█████▉    | 217/363 [00:11<00:03, 38.66it/s]
Loading 0:  61%|██████    | 222/363 [00:11<00:04, 33.13it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 41.27it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:03, 41.76it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:02, 43.05it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:02, 42.13it/s]
Loading 0:  69%|██████▉   | 250/363 [00:12<00:02, 41.26it/s]
Loading 0:  71%|███████   | 257/363 [00:12<00:02, 46.24it/s]
Loading 0:  72%|███████▏  | 262/363 [00:12<00:02, 46.05it/s]
Loading 0:  74%|███████▎  | 267/363 [00:13<00:02, 35.62it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 41.54it/s]
Loading 0:  77%|███████▋  | 279/363 [00:13<00:01, 42.15it/s]
Loading 0:  78%|███████▊  | 284/363 [00:13<00:02, 30.40it/s]
Loading 0:  79%|███████▉  | 288/363 [00:13<00:02, 31.81it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 33.55it/s]
Loading 0:  82%|████████▏ | 296/363 [00:13<00:02, 33.26it/s]
Loading 0:  83%|████████▎ | 301/363 [00:13<00:01, 35.87it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:01, 34.48it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 37.00it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:01, 36.25it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:01, 40.17it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:00, 42.07it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:00, 35.08it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 43.27it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 44.52it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 38.65it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 46.65it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 45.83it/s]
                                                            
Job chaiml-nemo-20241014-mer-7710-v2-mkmlizer completed after 98.81s with status: succeeded
Stopping job with name chaiml-nemo-20241014-mer-7710-v2-mkmlizer
Pipeline stage MKMLizer completed in 99.31s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241014-mer-7710-v2
Waiting for inference service chaiml-nemo-20241014-mer-7710-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission zonemercy-lexical-nemov8_5966_v2: HTTPConnectionPool(host='zonemercy-lexical-nemov8-5966-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x742240b01730>: Failed to establish a new connection: [Errno -5] No address associated with hostname'))
Inference service chaiml-nemo-20241014-mer-7710-v2 ready after 160.55163741111755s
Pipeline stage MKMLDeployer completed in 161.08s
run pipeline stage %s
Running pipeline stage StressChecker
Failed to get response for submission zonemercy-virgo-edit-v1-1e5_v13: HTTPConnectionPool(host='zonemercy-virgo-edit-v1-1e5-v13-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x742183cc6210>: Failed to establish a new connection: [Errno -5] No address associated with hostname'))
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Failed to get response for submission blend_lofer_2024-10-07: HTTPConnectionPool(host='blend-pifos-2024-10-07-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x74213c105250>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))
Failed to get response for submission zonemercy-virgo-edit-v1-1e5_v13: HTTPConnectionPool(host='zonemercy-virgo-edit-v1-1e5-v13-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x74212ef989b0>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Failed to get response for submission sao10k-mn-12b-lyra-v4a1_v3: HTTPConnectionPool(host='sao10k-mn-12b-lyra-v4a1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x74213c310a10>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))
Failed to get response for submission zonemercy-virgo-edit-v1-1e5_v13: HTTPConnectionPool(host='zonemercy-virgo-edit-v1-1e5-v13-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x742183e37d70>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Failed to get response for submission chaiml-nemo-20241010-t_5991_v160: HTTPConnectionPool(host='chaiml-nemo-20241010-t-5991-v160-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x74213c9a8e90>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Received healthy response to inference request in 68.65106964111328s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Received healthy response to inference request in 2.382308006286621s
Received healthy response to inference request in 2.3624515533447266s
Received healthy response to inference request in 1.754422903060913s
Received healthy response to inference request in 1.6503055095672607s
5 requests
0 failed requests
5th percentile: 1.6711289882659912
10th percentile: 1.6919524669647217
20th percentile: 1.7335994243621826
30th percentile: 1.8760286331176759
40th percentile: 2.119240093231201
50th percentile: 2.3624515533447266
60th percentile: 2.3703941345214843
70th percentile: 2.378336715698242
80th percentile: 15.636060333251965
90th percentile: 42.14356498718262
95th percentile: 55.39731731414794
99th percentile: 66.00031917572021
mean time: 15.360111522674561
Pipeline stage StressChecker completed in 78.45s
Shutdown handler de-registered
chaiml-nemo-20241014-mer_7710_v2 status is now deployed due to DeploymentManager action
chaiml-nemo-20241014-mer_7710_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241014-mer_7710_v2 status is now torndown due to DeploymentManager action