chaiml-lexical-nemov8-1k1e5

developer_uid: valentin87
submission_id: chaiml-lexical-nemov8-1k1e5_v25
model_name: chaiml-lexical-nemov8-1k1e5_v22
model_group: ChaiML/Lexical-Nemov8-1k
status: torndown
timestamp: 2024-10-23T15:07:33+00:00
num_battles: 7581
num_wins: 4093
celo_rating: 1273.64
family_friendly_score: 0.778
family_friendly_standard_error: 0.005877346339973509
submission_type: basic
model_repo: ChaiML/Lexical-Nemov8-1k1e5
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 16
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-lexical-nemov8-1k1e5_v22
is_internal_developer: True
language_model: ChaiML/Lexical-Nemov8-1k1e5
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-23
win_ratio: 0.5399023875478169
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|>'], 'max_input_tokens': 1024, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', '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-lexical-nemov8-1k1e5-v25-mkmlizer
Waiting for job on chaiml-lexical-nemov8-1k1e5-v25-mkmlizer to finish
chaiml-lexical-nemov8-1k1e5-v25-mkmlizer: Downloaded to shared memory in 67.998s
chaiml-lexical-nemov8-1k1e5-v25-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr8zg5mgx, device:0
chaiml-lexical-nemov8-1k1e5-v25-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-lexical-nemov8-1k1e5-v25-mkmlizer: quantized model in 47.148s
chaiml-lexical-nemov8-1k1e5-v25-mkmlizer: Processed model ChaiML/Lexical-Nemov8-1k1e5 in 115.146s
chaiml-lexical-nemov8-1k1e5-v25-mkmlizer: creating bucket guanaco-mkml-models
chaiml-lexical-nemov8-1k1e5-v25-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-lexical-nemov8-1k1e5-v25-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v25
chaiml-lexical-nemov8-1k1e5-v25-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v25/config.json
chaiml-lexical-nemov8-1k1e5-v25-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v25/special_tokens_map.json
chaiml-lexical-nemov8-1k1e5-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v25/tokenizer_config.json
chaiml-lexical-nemov8-1k1e5-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v25/tokenizer.json
chaiml-lexical-nemov8-1k1e5-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v25/flywheel_model.0.safetensors
chaiml-lexical-nemov8-1k1e5-v25-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:22, 15.98it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:59,  5.97it/s]
Loading 0:   2%|▏         | 8/363 [00:01<00:52,  6.80it/s]
Loading 0:   2%|▏         | 9/363 [00:01<00:54,  6.55it/s]
Loading 0:   3%|▎         | 10/363 [00:01<00:50,  7.01it/s]
Loading 0:   3%|▎         | 12/363 [00:01<01:09,  5.04it/s]
Loading 0:   4%|▎         | 13/363 [00:02<01:38,  3.54it/s]
Loading 0:   4%|▍         | 14/363 [00:02<01:49,  3.19it/s]
Loading 0:   5%|▍         | 18/363 [00:03<00:52,  6.54it/s]
Loading 0:   6%|▌         | 20/363 [00:03<00:42,  8.12it/s]
Loading 0:   6%|▌         | 22/363 [00:03<00:37,  9.03it/s]
Loading 0:   7%|▋         | 24/363 [00:03<00:41,  8.14it/s]
Loading 0:   7%|▋         | 26/363 [00:03<00:41,  8.16it/s]
Loading 0:   8%|▊         | 30/363 [00:04<00:28, 11.76it/s]
Loading 0:   9%|▉         | 32/363 [00:04<00:30, 10.79it/s]
Loading 0:  10%|█         | 37/363 [00:04<00:19, 16.86it/s]
Loading 0:  11%|█         | 40/363 [00:04<00:17, 18.70it/s]
Loading 0:  12%|█▏        | 43/363 [00:04<00:16, 19.69it/s]
Loading 0:  13%|█▎        | 46/363 [00:04<00:16, 18.74it/s]
Loading 0:  13%|█▎        | 49/363 [00:05<00:28, 11.05it/s]
Loading 0:  14%|█▍        | 51/363 [00:05<00:33,  9.43it/s]
Loading 0:  15%|█▍        | 54/363 [00:05<00:25, 11.94it/s]
Loading 0:  15%|█▌        | 56/363 [00:05<00:26, 11.42it/s]
Loading 0:  17%|█▋        | 60/363 [00:06<00:19, 15.32it/s]
Loading 0:  17%|█▋        | 63/363 [00:06<00:22, 13.45it/s]
Loading 0:  18%|█▊        | 65/363 [00:06<00:21, 14.04it/s]
Loading 0:  20%|█▉        | 71/363 [00:06<00:14, 20.29it/s]
Loading 0:  20%|██        | 74/363 [00:06<00:13, 21.79it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:15, 18.48it/s]
Loading 0:  23%|██▎       | 82/363 [00:07<00:11, 24.30it/s]
Loading 0:  23%|██▎       | 85/363 [00:07<00:11, 25.05it/s]
Loading 0:  24%|██▍       | 88/363 [00:07<00:11, 24.79it/s]
Loading 0:  26%|██▌       | 93/363 [00:07<00:09, 27.40it/s]
Loading 0:  26%|██▋       | 96/363 [00:07<00:11, 23.41it/s]
Loading 0:  28%|██▊       | 100/363 [00:07<00:09, 26.89it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:14, 18.36it/s]
Loading 0:  29%|██▉       | 106/363 [00:08<00:13, 19.35it/s]
Loading 0:  31%|███       | 111/363 [00:08<00:10, 23.03it/s]
Loading 0:  31%|███▏      | 114/363 [00:08<00:11, 21.40it/s]
Loading 0:  33%|███▎      | 118/363 [00:08<00:09, 25.18it/s]
Loading 0:  33%|███▎      | 121/363 [00:08<00:09, 24.93it/s]
Loading 0:  34%|███▍      | 124/363 [00:08<00:09, 24.55it/s]
Loading 0:  36%|███▌      | 129/363 [00:09<00:08, 26.82it/s]
Loading 0:  36%|███▋      | 132/363 [00:09<00:09, 23.69it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:08, 27.16it/s]
Loading 0:  39%|███▉      | 141/363 [00:09<00:07, 28.43it/s]
Loading 0:  40%|███▉      | 144/363 [00:09<00:12, 17.16it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:10, 20.15it/s]
Loading 0:  42%|████▏     | 151/363 [00:10<00:10, 20.38it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:09, 22.18it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:08, 23.20it/s]
Loading 0:  44%|████▍     | 160/363 [00:10<00:08, 22.99it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:08, 24.60it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:07, 25.27it/s]
Loading 0:  47%|████▋     | 169/363 [00:10<00:07, 24.74it/s]
Loading 0:  48%|████▊     | 174/363 [00:11<00:06, 27.46it/s]
Loading 0:  49%|████▉     | 177/363 [00:11<00:07, 24.14it/s]
Loading 0:  50%|████▉     | 181/363 [00:11<00:06, 27.65it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:09, 18.15it/s]
Loading 0:  52%|█████▏    | 187/363 [00:11<00:09, 19.03it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:08, 21.13it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:07, 22.54it/s]
Loading 0:  54%|█████▍    | 196/363 [00:12<00:07, 23.10it/s]
Loading 0:  55%|█████▌    | 201/363 [00:12<00:06, 25.70it/s]
Loading 0:  56%|█████▌    | 204/363 [00:12<00:06, 22.87it/s]
Loading 0:  58%|█████▊    | 210/363 [00:12<00:05, 27.11it/s]
Loading 0:  59%|█████▊    | 213/363 [00:12<00:06, 24.47it/s]
Loading 0:  60%|██████    | 218/363 [00:12<00:05, 27.48it/s]
Loading 0:  61%|██████▏   | 223/363 [00:13<00:06, 22.58it/s]
Loading 0:  62%|██████▏   | 226/363 [00:13<00:06, 21.41it/s]
Loading 0:  63%|██████▎   | 230/363 [00:13<00:06, 20.84it/s]
Loading 0:  65%|██████▍   | 235/363 [00:13<00:05, 25.54it/s]
Loading 0:  66%|██████▌   | 239/363 [00:13<00:05, 23.45it/s]
Loading 0:  67%|██████▋   | 244/363 [00:13<00:04, 28.51it/s]
Loading 0:  68%|██████▊   | 248/363 [00:14<00:04, 24.29it/s]
Loading 0:  70%|███████   | 255/363 [00:14<00:03, 30.47it/s]
Loading 0:  71%|███████▏  | 259/363 [00:14<00:03, 28.95it/s]
Loading 0:  72%|███████▏  | 263/363 [00:14<00:04, 22.42it/s]
Loading 0:  73%|███████▎  | 266/363 [00:15<00:05, 18.73it/s]
Loading 0:  75%|███████▍  | 271/363 [00:15<00:03, 23.85it/s]
Loading 0:  76%|███████▌  | 275/363 [00:15<00:04, 21.33it/s]
Loading 0:  77%|███████▋  | 280/363 [00:15<00:03, 26.12it/s]
Loading 0:  78%|███████▊  | 284/363 [00:15<00:03, 22.90it/s]
Loading 0:  80%|███████▉  | 289/363 [00:15<00:02, 27.76it/s]
Loading 0:  81%|████████  | 293/363 [00:16<00:02, 23.96it/s]
Loading 0:  82%|████████▏ | 299/363 [00:16<00:02, 27.58it/s]
Loading 0:  84%|████████▎ | 304/363 [00:16<00:02, 23.96it/s]
Loading 0:  85%|████████▍ | 307/363 [00:16<00:02, 22.13it/s]
Loading 0:  85%|████████▌ | 310/363 [00:16<00:02, 23.00it/s]
Loading 0:  86%|████████▌ | 313/363 [00:16<00:02, 24.05it/s]
Loading 0:  87%|████████▋ | 316/363 [00:16<00:01, 25.10it/s]
Loading 0:  88%|████████▊ | 320/363 [00:17<00:01, 22.95it/s]
Loading 0:  90%|█████████ | 327/363 [00:17<00:01, 30.04it/s]
Loading 0:  91%|█████████ | 331/363 [00:17<00:01, 27.69it/s]
Loading 0:  93%|█████████▎| 336/363 [00:17<00:00, 29.91it/s]
Loading 0:  94%|█████████▎| 340/363 [00:17<00:00, 27.76it/s]
Loading 0:  94%|█████████▍| 343/363 [00:17<00:00, 27.67it/s]
Loading 0:  95%|█████████▌| 346/363 [00:25<00:10,  1.65it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:07,  1.97it/s]
Loading 0:  97%|█████████▋| 353/363 [00:25<00:03,  3.18it/s]
Loading 0:  98%|█████████▊| 357/363 [00:25<00:01,  4.34it/s]
                                                            
Job chaiml-lexical-nemov8-1k1e5-v25-mkmlizer completed after 144.67s with status: succeeded
Stopping job with name chaiml-lexical-nemov8-1k1e5-v25-mkmlizer
Pipeline stage MKMLizer completed in 145.19s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-lexical-nemov8-1k1e5-v25
Waiting for inference service chaiml-lexical-nemov8-1k1e5-v25 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service chaiml-lexical-nemov8-1k1e5-v25 ready after 130.46718215942383s
Pipeline stage MKMLDeployer completed in 131.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3342928886413574s
Received healthy response to inference request in 1.6922485828399658s
Received healthy response to inference request in 1.9738245010375977s
Received healthy response to inference request in 6.621086359024048s
Received healthy response to inference request in 1.9568796157836914s
5 requests
0 failed requests
5th percentile: 1.7451747894287108
10th percentile: 1.798100996017456
20th percentile: 1.9039534091949464
30th percentile: 1.9602685928344727
40th percentile: 1.9670465469360352
50th percentile: 1.9738245010375977
60th percentile: 2.1180118560791015
70th percentile: 2.2621992111206053
80th percentile: 3.1916515827178964
90th percentile: 4.906368970870972
95th percentile: 5.763727664947509
99th percentile: 6.44961462020874
mean time: 2.915666389465332
Pipeline stage StressChecker completed in 15.92s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 7.59s
Shutdown handler de-registered
chaiml-lexical-nemov8-1k1e5_v25 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2438.06s
Shutdown handler de-registered
chaiml-lexical-nemov8-1k1e5_v25 status is now inactive due to auto deactivation removed underperforming models
chaiml-lexical-nemov8-1k1e5_v25 status is now torndown due to DeploymentManager action