developer_uid: chai_backend_admin
submission_id: zonemercy-lexical-viral-_3982_v4
model_name: tempv1-1
model_group: zonemercy/Lexical-Viral-
status: inactive
timestamp: 2024-11-19T14:22:21+00:00
num_battles: 11682
num_wins: 6146
celo_rating: 1271.54
family_friendly_score: 0.5942000000000001
family_friendly_standard_error: 0.006944441806221721
submission_type: basic
model_repo: zonemercy/Lexical-Viral-v6ava-22b11e5r256
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3842199661064779, 'latency_mean': 2.6025889825820925, 'latency_p50': 2.5971518754959106, 'latency_p90': 2.884085011482239}, {'batch_size': 3, 'throughput': 0.8155722525854006, 'latency_mean': 3.6631567847728728, 'latency_p50': 3.6307029724121094, 'latency_p90': 4.007800579071045}, {'batch_size': 5, 'throughput': 1.0812360624846145, 'latency_mean': 4.603507347106934, 'latency_p50': 4.565229177474976, 'latency_p90': 5.227538275718689}, {'batch_size': 6, 'throughput': 1.1574189727224744, 'latency_mean': 5.142365885972977, 'latency_p50': 5.1569825410842896, 'latency_p90': 5.780669116973876}, {'batch_size': 10, 'throughput': 1.3797550024179983, 'latency_mean': 7.185764673948288, 'latency_p50': 7.169527053833008, 'latency_p90': 8.007778429985047}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: tempv1-1
is_internal_developer: True
language_model: zonemercy/Lexical-Viral-v6ava-22b11e5r256
model_size: 22B
ranking_group: single
throughput_3p7s: 0.83
us_pacific_date: 2024-11-19
win_ratio: 0.5261085430576956
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': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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 zonemercy-lexical-viral-3982-v4-mkmlizer
Waiting for job on zonemercy-lexical-viral-3982-v4-mkmlizer to finish
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
zonemercy-lexical-viral-3982-v4-mkmlizer: Downloaded to shared memory in 94.125s
zonemercy-lexical-viral-3982-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5ac3rvh5, device:0
zonemercy-lexical-viral-3982-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-lexical-viral-3982-v4-mkmlizer: quantized model in 48.798s
zonemercy-lexical-viral-3982-v4-mkmlizer: Processed model zonemercy/Lexical-Viral-v6ava-22b11e5r256 in 142.923s
zonemercy-lexical-viral-3982-v4-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-lexical-viral-3982-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-lexical-viral-3982-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-lexical-viral-3982-v4
zonemercy-lexical-viral-3982-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-lexical-viral-3982-v4/config.json
zonemercy-lexical-viral-3982-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-lexical-viral-3982-v4/special_tokens_map.json
zonemercy-lexical-viral-3982-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-lexical-viral-3982-v4/tokenizer_config.json
zonemercy-lexical-viral-3982-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-lexical-viral-3982-v4/tokenizer.json
Retrying (%r) after connection broken by '%r': %s
zonemercy-lexical-viral-3982-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-lexical-viral-3982-v4/flywheel_model.1.safetensors
zonemercy-lexical-viral-3982-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-lexical-viral-3982-v4/flywheel_model.0.safetensors
zonemercy-lexical-viral-3982-v4-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 4/507 [00:00<00:14, 34.88it/s] Loading 0: 2%|▏ | 8/507 [00:00<00:19, 26.21it/s] Loading 0: 2%|▏ | 11/507 [00:00<00:18, 27.00it/s] Loading 0: 3%|▎ | 14/507 [00:00<00:23, 21.26it/s] Loading 0: 4%|▎ | 19/507 [00:00<00:17, 27.25it/s] Loading 0: 5%|▍ | 23/507 [00:00<00:19, 24.67it/s] Loading 0: 6%|▌ | 28/507 [00:01<00:16, 28.63it/s] Loading 0: 6%|▋ | 32/507 [00:01<00:19, 24.48it/s] Loading 0: 7%|▋ | 37/507 [00:01<00:16, 28.18it/s] Loading 0: 8%|▊ | 41/507 [00:01<00:17, 26.31it/s] Loading 0: 9%|▉ | 46/507 [00:01<00:14, 31.06it/s] Loading 0: 10%|▉ | 50/507 [00:01<00:15, 29.07it/s] Loading 0: 11%|█ | 54/507 [00:02<00:22, 20.42it/s] Loading 0: 11%|█ | 57/507 [00:02<00:22, 20.37it/s] Loading 0: 12%|█▏ | 61/507 [00:02<00:19, 23.25it/s] Loading 0: 13%|█▎ | 65/507 [00:02<00:20, 22.07it/s] Loading 0: 14%|█▍ | 70/507 [00:02<00:16, 26.33it/s] Loading 0: 14%|█▍ | 73/507 [00:02<00:16, 26.36it/s] Loading 0: 16%|█▌ | 79/507 [00:02<00:12, 33.35it/s] Loading 0: 16%|█▋ | 83/507 [00:03<00:13, 31.66it/s] Loading 0: 17%|█▋ | 87/507 [00:03<00:13, 30.31it/s] Loading 0: 18%|█▊ | 91/507 [00:03<00:14, 28.63it/s] Loading 0: 19%|█▊ | 94/507 [00:03<00:14, 28.13it/s] Loading 0: 19%|█▉ | 98/507 [00:03<00:16, 25.01it/s] Loading 0: 20%|██ | 103/507 [00:03<00:14, 27.92it/s] Loading 0: 21%|██ | 107/507 [00:04<00:15, 25.96it/s] Loading 0: 22%|██▏ | 112/507 [00:04<00:13, 29.44it/s] Loading 0: 23%|██▎ | 116/507 [00:04<00:21, 18.34it/s] Loading 0: 24%|██▍ | 122/507 [00:04<00:18, 21.21it/s] Loading 0: 25%|██▌ | 127/507 [00:04<00:15, 24.87it/s] Loading 0: 26%|██▌ | 131/507 [00:05<00:15, 23.73it/s] Loading 0: 27%|██▋ | 136/507 [00:05<00:13, 26.63it/s] Loading 0: 28%|██▊ | 140/507 [00:05<00:15, 24.32it/s] Loading 0: 29%|██▊ | 145/507 [00:05<00:13, 27.51it/s] Loading 0: 29%|██▉ | 149/507 [00:05<00:14, 25.38it/s] Loading 0: 30%|███ | 154/507 [00:05<00:12, 28.65it/s] Loading 0: 31%|███ | 158/507 [00:06<00:13, 26.64it/s] Loading 0: 32%|███▏ | 163/507 [00:06<00:11, 29.45it/s] Loading 0: 33%|███▎ | 168/507 [00:06<00:10, 31.64it/s] Loading 0: 34%|███▍ | 172/507 [00:06<00:15, 21.49it/s] Loading 0: 35%|███▍ | 176/507 [00:06<00:15, 21.77it/s] Loading 0: 36%|███▌ | 181/507 [00:07<00:12, 25.96it/s] Loading 0: 36%|███▋ | 185/507 [00:07<00:12, 25.09it/s] Loading 0: 37%|███▋ | 190/507 [00:07<00:10, 29.17it/s] Loading 0: 38%|███▊ | 194/507 [00:07<00:11, 27.44it/s] Loading 0: 39%|███▉ | 199/507 [00:07<00:09, 31.10it/s] Loading 0: 40%|████ | 203/507 [00:07<00:10, 28.42it/s] Loading 0: 41%|████ | 208/507 [00:07<00:09, 32.42it/s] Loading 0: 42%|████▏ | 212/507 [00:08<00:10, 29.28it/s] Loading 0: 43%|████▎ | 217/507 [00:08<00:08, 33.26it/s] Loading 0: 44%|████▎ | 221/507 [00:08<00:09, 30.20it/s] Loading 0: 44%|████▍ | 225/507 [00:08<00:12, 21.81it/s] Loading 0: 45%|████▌ | 230/507 [00:08<00:11, 23.67it/s] Loading 0: 46%|████▋ | 235/507 [00:08<00:09, 27.64it/s] Loading 0: 47%|████▋ | 239/507 [00:09<00:10, 25.84it/s] Loading 0: 48%|████▊ | 244/507 [00:09<00:08, 29.46it/s] Loading 0: 49%|████▉ | 248/507 [00:09<00:09, 26.82it/s] Loading 0: 50%|████▉ | 253/507 [00:09<00:08, 30.54it/s] Loading 0: 51%|█████ | 257/507 [00:09<00:09, 27.39it/s] Loading 0: 52%|█████▏ | 262/507 [00:09<00:07, 30.75it/s] Loading 0: 52%|█████▏ | 266/507 [00:10<00:08, 27.06it/s] Loading 0: 53%|█████▎ | 271/507 [00:10<00:07, 30.26it/s] Loading 0: 54%|█████▍ | 275/507 [00:10<00:08, 27.72it/s] Loading 0: 55%|█████▌ | 280/507 [00:10<00:07, 31.32it/s] Loading 0: 56%|█████▌ | 284/507 [00:10<00:09, 22.72it/s] Loading 0: 57%|█████▋ | 287/507 [00:10<00:10, 21.18it/s] Loading 0: 58%|█████▊ | 293/507 [00:11<00:08, 24.03it/s] Loading 0: 59%|█████▉ | 298/507 [00:11<00:07, 27.98it/s] Loading 0: 59%|█████▉ | 299/507 [00:26<00:07, 27.98it/s] Loading 0: 59%|█████▉ | 300/507 [00:26<04:03, 1.18s/it] Loading 0: 60%|█████▉ | 302/507 [00:26<03:20, 1.02it/s] Loading 0: 61%|██████ | 307/507 [00:26<02:01, 1.64it/s] Loading 0: 61%|██████ | 310/507 [00:26<01:32, 2.14it/s] Loading 0: 62%|██████▏ | 313/507 [00:26<01:08, 2.82it/s] Loading 0: 62%|██████▏ | 316/507 [00:26<00:50, 3.75it/s] Loading 0: 63%|██████▎ | 320/507 [00:26<00:35, 5.27it/s] Loading 0: 64%|██████▍ | 325/507 [00:27<00:22, 7.96it/s] Loading 0: 65%|██████▍ | 329/507 [00:27<00:17, 9.98it/s] Loading 0: 66%|██████▌ | 334/507 [00:27<00:12, 13.73it/s] Loading 0: 67%|██████▋ | 339/507 [00:27<00:09, 17.40it/s] Loading 0: 68%|██████▊ | 343/507 [00:27<00:10, 15.42it/s] Loading 0: 68%|██████▊ | 347/507 [00:28<00:09, 16.81it/s] Loading 0: 69%|██████▉ | 352/507 [00:28<00:07, 21.18it/s] Loading 0: 70%|███████ | 356/507 [00:28<00:06, 21.67it/s] Loading 0: 71%|███████ | 361/507 [00:28<00:05, 26.12it/s] Loading 0: 72%|███████▏ | 365/507 [00:28<00:05, 24.57it/s] Loading 0: 73%|███████▎ | 370/507 [00:28<00:04, 28.95it/s] Loading 0: 74%|███████▍ | 374/507 [00:28<00:04, 27.53it/s] Loading 0: 75%|███████▍ | 379/507 [00:28<00:03, 32.16it/s] Loading 0: 76%|███████▌ | 383/507 [00:29<00:04, 29.37it/s] Loading 0: 77%|███████▋ | 388/507 [00:29<00:03, 33.67it/s] Loading 0: 77%|███████▋ | 392/507 [00:29<00:03, 30.89it/s] Loading 0: 78%|███████▊ | 396/507 [00:29<00:05, 22.14it/s] Loading 0: 79%|███████▉ | 401/507 [00:29<00:04, 23.85it/s] Loading 0: 80%|████████ | 406/507 [00:30<00:03, 27.97it/s] Loading 0: 81%|████████ | 410/507 [00:30<00:03, 26.14it/s] Loading 0: 82%|████████▏ | 415/507 [00:30<00:03, 30.20it/s] Loading 0: 83%|████████▎ | 419/507 [00:30<00:03, 28.05it/s] Loading 0: 84%|████████▎ | 424/507 [00:30<00:02, 31.98it/s] Loading 0: 84%|████████▍ | 428/507 [00:30<00:02, 29.71it/s] Loading 0: 85%|████████▌ | 433/507 [00:30<00:02, 33.77it/s] Loading 0: 86%|████████▌ | 437/507 [00:31<00:02, 30.39it/s] Loading 0: 87%|████████▋ | 442/507 [00:31<00:01, 34.38it/s] Loading 0: 88%|████████▊ | 446/507 [00:31<00:01, 30.77it/s] Loading 0: 89%|████████▉ | 451/507 [00:31<00:01, 34.80it/s] Loading 0: 90%|████████▉ | 455/507 [00:33<00:09, 5.41it/s] Loading 0: 91%|█████████ | 459/507 [00:34<00:07, 6.85it/s] Loading 0: 92%|█████████▏| 465/507 [00:34<00:04, 9.65it/s] Loading 0: 93%|█████████▎| 470/507 [00:34<00:02, 12.71it/s] Loading 0: 93%|█████████▎| 474/507 [00:34<00:02, 14.36it/s] Loading 0: 94%|█████████▍| 479/507 [00:34<00:01, 18.23it/s] Loading 0: 95%|█████████▌| 483/507 [00:34<00:01, 19.28it/s] Loading 0: 96%|█████████▋| 488/507 [00:34<00:00, 23.53it/s] Loading 0: 97%|█████████▋| 492/507 [00:35<00:00, 23.23it/s] Loading 0: 98%|█████████▊| 497/507 [00:35<00:00, 27.35it/s] Loading 0: 99%|█████████▉| 501/507 [00:35<00:00, 25.32it/s] Loading 0: 100%|█████████▉| 506/507 [00:35<00:00, 29.35it/s]
Job zonemercy-lexical-viral-3982-v4-mkmlizer completed after 186.23s with status: succeeded
Stopping job with name zonemercy-lexical-viral-3982-v4-mkmlizer
Pipeline stage MKMLizer completed in 186.86s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-lexical-viral-3982-v4
Waiting for inference service zonemercy-lexical-viral-3982-v4 to be ready
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-lexical-viral-3982-v4 ready after 200.72861456871033s
Pipeline stage MKMLDeployer completed in 201.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0829403400421143s
Received healthy response to inference request in 3.291085958480835s
Received healthy response to inference request in 2.658419609069824s
Received healthy response to inference request in 2.5340464115142822s
Received healthy response to inference request in 2.5904152393341064s
5 requests
0 failed requests
5th percentile: 2.545320177078247
10th percentile: 2.5565939426422117
20th percentile: 2.5791414737701417
30th percentile: 2.60401611328125
40th percentile: 2.631217861175537
50th percentile: 2.658419609069824
60th percentile: 2.82822790145874
70th percentile: 2.998036193847656
80th percentile: 3.124569463729858
90th percentile: 3.2078277111053466
95th percentile: 3.249456834793091
99th percentile: 3.2827601337432863
mean time: 2.8313815116882326
Pipeline stage StressChecker completed in 15.55s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.24s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.75s
Shutdown handler de-registered
zonemercy-lexical-viral-_3982_v4 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
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 3190.92s
Shutdown handler de-registered
zonemercy-lexical-viral-_3982_v4 status is now inactive due to auto deactivation removed underperforming models