developer_uid: azuruce
submission_id: chaiml-espresso-ant-2412_3236_v1
model_name: chaiml-espresso-ant-2412_3236_v1
model_group: ChaiML/espresso_ant_2412
status: inactive
timestamp: 2024-12-03T08:14:16+00:00
num_battles: 13714
num_wins: 6707
celo_rating: 1253.98
family_friendly_score: 0.5913999999999999
family_friendly_standard_error: 0.006951921173316049
submission_type: basic
model_repo: ChaiML/espresso_ant_241202_albert_v1_2e
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.38131117623473554, 'latency_mean': 2.6224336433410644, 'latency_p50': 2.6100218296051025, 'latency_p90': 2.9106894731521606}, {'batch_size': 2, 'throughput': 0.5932300471392835, 'latency_mean': 3.369961692094803, 'latency_p50': 3.383974552154541, 'latency_p90': 3.7311259746551513}, {'batch_size': 3, 'throughput': 0.7516398786116821, 'latency_mean': 3.9746113908290863, 'latency_p50': 3.9661628007888794, 'latency_p90': 4.350516629219055}, {'batch_size': 4, 'throughput': 0.871321710845268, 'latency_mean': 4.570208413600922, 'latency_p50': 4.5753103494644165, 'latency_p90': 5.1201266050338745}, {'batch_size': 5, 'throughput': 0.9606582226065925, 'latency_mean': 5.191882606744766, 'latency_p50': 5.221438646316528, 'latency_p90': 5.8432104825973505}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-espresso-ant-2412_3236_v1
is_internal_developer: True
language_model: ChaiML/espresso_ant_241202_albert_v1_2e
model_size: 22B
ranking_group: single
throughput_3p7s: 0.69
us_pacific_date: 2024-12-03
win_ratio: 0.4890622721306694
generation_params: {'temperature': 0.9, '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': '', '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 chaiml-espresso-ant-2412-3236-v1-mkmlizer
Waiting for job on chaiml-espresso-ant-2412-3236-v1-mkmlizer to finish
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ _____ __ __ ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ /___/ ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ belonging to: ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ║ ║
chaiml-espresso-ant-2412-3236-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-2412-3236-v1-mkmlizer: Downloaded to shared memory in 79.283s
chaiml-espresso-ant-2412-3236-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgq_3hvhp, device:0
chaiml-espresso-ant-2412-3236-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-2412-3236-v1-mkmlizer: quantized model in 45.340s
chaiml-espresso-ant-2412-3236-v1-mkmlizer: Processed model ChaiML/espresso_ant_241202_albert_v1_2e in 124.624s
chaiml-espresso-ant-2412-3236-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-2412-3236-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-2412-3236-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-2412-3236-v1
chaiml-espresso-ant-2412-3236-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-3236-v1/config.json
chaiml-espresso-ant-2412-3236-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-3236-v1/special_tokens_map.json
chaiml-espresso-ant-2412-3236-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-3236-v1/tokenizer_config.json
chaiml-espresso-ant-2412-3236-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-3236-v1/tokenizer.json
chaiml-espresso-ant-2412-3236-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-2412-3236-v1/flywheel_model.1.safetensors
chaiml-espresso-ant-2412-3236-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-2412-3236-v1/flywheel_model.0.safetensors
chaiml-espresso-ant-2412-3236-v1-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 5/507 [00:00<00:21, 23.71it/s] Loading 0: 2%|▏ | 12/507 [00:00<00:12, 40.66it/s] Loading 0: 3%|▎ | 17/507 [00:00<00:12, 37.80it/s] Loading 0: 4%|▍ | 22/507 [00:00<00:12, 39.01it/s] Loading 0: 5%|▌ | 27/507 [00:00<00:11, 40.15it/s] Loading 0: 6%|▋ | 32/507 [00:00<00:14, 33.68it/s] Loading 0: 8%|▊ | 39/507 [00:01<00:11, 40.89it/s] Loading 0: 9%|▊ | 44/507 [00:01<00:11, 40.51it/s] Loading 0: 10%|▉ | 49/507 [00:01<00:13, 34.02it/s] Loading 0: 10%|█ | 53/507 [00:01<00:17, 26.51it/s] Loading 0: 11%|█ | 57/507 [00:01<00:17, 26.28it/s] Loading 0: 12%|█▏ | 63/507 [00:01<00:14, 31.56it/s] Loading 0: 13%|█▎ | 67/507 [00:01<00:13, 32.35it/s] Loading 0: 14%|█▍ | 73/507 [00:02<00:12, 35.29it/s] Loading 0: 16%|█▌ | 80/507 [00:02<00:11, 36.62it/s] Loading 0: 17%|█▋ | 87/507 [00:02<00:10, 41.98it/s] Loading 0: 18%|█▊ | 92/507 [00:02<00:10, 40.77it/s] Loading 0: 19%|█▉ | 97/507 [00:02<00:10, 39.84it/s] Loading 0: 20%|██ | 102/507 [00:02<00:10, 38.21it/s] Loading 0: 21%|██ | 106/507 [00:02<00:11, 35.94it/s] Loading 0: 22%|██▏ | 110/507 [00:03<00:11, 35.43it/s] Loading 0: 22%|██▏ | 114/507 [00:03<00:15, 24.77it/s] Loading 0: 23%|██▎ | 117/507 [00:03<00:16, 24.11it/s] Loading 0: 24%|██▍ | 122/507 [00:03<00:15, 24.97it/s] Loading 0: 25%|██▌ | 129/507 [00:03<00:11, 31.71it/s] Loading 0: 26%|██▌ | 133/507 [00:03<00:12, 31.02it/s] Loading 0: 27%|██▋ | 138/507 [00:04<00:10, 33.85it/s] Loading 0: 28%|██▊ | 142/507 [00:04<00:11, 32.06it/s] Loading 0: 29%|██▉ | 147/507 [00:04<00:10, 34.71it/s] Loading 0: 30%|██▉ | 151/507 [00:04<00:10, 32.76it/s] Loading 0: 31%|███ | 156/507 [00:04<00:09, 35.52it/s] Loading 0: 32%|███▏ | 160/507 [00:04<00:09, 35.08it/s] Loading 0: 32%|███▏ | 164/507 [00:04<00:09, 35.15it/s] Loading 0: 33%|███▎ | 169/507 [00:05<00:12, 27.45it/s] Loading 0: 34%|███▍ | 173/507 [00:05<00:11, 27.98it/s] Loading 0: 35%|███▍ | 177/507 [00:05<00:12, 26.99it/s] Loading 0: 36%|███▌ | 183/507 [00:05<00:10, 32.10it/s] Loading 0: 37%|███▋ | 187/507 [00:05<00:10, 31.12it/s] Loading 0: 38%|███▊ | 192/507 [00:05<00:09, 33.93it/s] Loading 0: 39%|███▊ | 196/507 [00:05<00:09, 33.22it/s] Loading 0: 40%|███▉ | 201/507 [00:06<00:08, 36.23it/s] Loading 0: 40%|████ | 205/507 [00:06<00:08, 35.09it/s] Loading 0: 41%|████▏ | 210/507 [00:06<00:08, 36.79it/s] Loading 0: 42%|████▏ | 214/507 [00:06<00:08, 35.03it/s] Loading 0: 43%|████▎ | 218/507 [00:06<00:08, 36.04it/s] Loading 0: 44%|████▍ | 222/507 [00:06<00:07, 36.20it/s] Loading 0: 45%|████▍ | 226/507 [00:06<00:10, 25.88it/s] Loading 0: 45%|████▌ | 230/507 [00:07<00:11, 25.18it/s] Loading 0: 46%|████▋ | 235/507 [00:07<00:09, 29.98it/s] Loading 0: 47%|████▋ | 239/507 [00:07<00:09, 27.82it/s] Loading 0: 48%|████▊ | 244/507 [00:07<00:08, 31.54it/s] Loading 0: 49%|████▉ | 248/507 [00:07<00:08, 29.18it/s] Loading 0: 50%|████▉ | 253/507 [00:07<00:07, 33.81it/s] Loading 0: 51%|█████ | 257/507 [00:07<00:08, 30.54it/s] Loading 0: 52%|█████▏ | 264/507 [00:08<00:06, 36.98it/s] Loading 0: 53%|█████▎ | 268/507 [00:08<00:07, 34.13it/s] Loading 0: 54%|█████▍ | 273/507 [00:08<00:06, 35.72it/s] Loading 0: 55%|█████▍ | 277/507 [00:08<00:06, 34.19it/s] Loading 0: 56%|█████▌ | 282/507 [00:08<00:05, 37.55it/s] Loading 0: 56%|█████▋ | 286/507 [00:08<00:08, 25.92it/s] Loading 0: 57%|█████▋ | 290/507 [00:08<00:07, 27.50it/s] Loading 0: 58%|█████▊ | 294/507 [00:09<00:08, 26.29it/s] Loading 0: 59%|█████▉ | 298/507 [00:09<00:07, 29.14it/s] Loading 0: 59%|█████▉ | 299/507 [00:23<00:07, 29.14it/s] Loading 0: 59%|█████▉ | 300/507 [00:23<04:24, 1.28s/it] Loading 0: 60%|█████▉ | 302/507 [00:24<03:34, 1.05s/it] Loading 0: 61%|██████ | 307/507 [00:24<02:05, 1.59it/s] Loading 0: 61%|██████ | 310/507 [00:24<01:33, 2.10it/s] Loading 0: 62%|██████▏ | 313/507 [00:24<01:09, 2.81it/s] Loading 0: 62%|██████▏ | 316/507 [00:24<00:51, 3.74it/s] Loading 0: 63%|██████▎ | 320/507 [00:24<00:35, 5.33it/s] Loading 0: 64%|██████▍ | 327/507 [00:24<00:19, 9.26it/s] Loading 0: 65%|██████▌ | 331/507 [00:24<00:15, 11.45it/s] Loading 0: 66%|██████▌ | 335/507 [00:25<00:12, 14.11it/s] Loading 0: 67%|██████▋ | 340/507 [00:25<00:10, 15.36it/s] Loading 0: 68%|██████▊ | 344/507 [00:25<00:09, 17.72it/s] Loading 0: 68%|██████▊ | 347/507 [00:25<00:09, 17.77it/s] Loading 0: 70%|██████▉ | 354/507 [00:25<00:06, 25.19it/s] Loading 0: 71%|███████ | 358/507 [00:25<00:05, 26.12it/s] Loading 0: 72%|███████▏ | 363/507 [00:26<00:04, 29.64it/s] Loading 0: 72%|███████▏ | 367/507 [00:26<00:04, 29.81it/s] Loading 0: 73%|███████▎ | 372/507 [00:26<00:04, 33.01it/s] Loading 0: 74%|███████▍ | 376/507 [00:26<00:03, 32.85it/s] Loading 0: 75%|███████▌ | 381/507 [00:26<00:03, 36.04it/s] Loading 0: 76%|███████▌ | 385/507 [00:26<00:03, 35.01it/s] Loading 0: 77%|███████▋ | 389/507 [00:26<00:03, 35.45it/s] Loading 0: 78%|███████▊ | 393/507 [00:26<00:03, 34.47it/s] Loading 0: 78%|███████▊ | 397/507 [00:27<00:04, 24.21it/s] Loading 0: 79%|███████▉ | 401/507 [00:27<00:04, 23.97it/s] Loading 0: 80%|████████ | 406/507 [00:27<00:03, 29.06it/s] Loading 0: 81%|████████ | 410/507 [00:27<00:03, 26.97it/s] Loading 0: 82%|████████▏ | 415/507 [00:27<00:02, 31.32it/s] Loading 0: 83%|████████▎ | 419/507 [00:27<00:03, 28.94it/s] Loading 0: 84%|████████▎ | 424/507 [00:27<00:02, 33.51it/s] Loading 0: 84%|████████▍ | 428/507 [00:28<00:02, 30.10it/s] Loading 0: 85%|████████▌ | 433/507 [00:28<00:02, 34.06it/s] Loading 0: 86%|████████▌ | 437/507 [00:28<00:02, 31.15it/s] Loading 0: 88%|████████▊ | 444/507 [00:28<00:01, 38.20it/s] Loading 0: 89%|████████▊ | 449/507 [00:28<00:01, 37.24it/s] Loading 0: 90%|████████▉ | 454/507 [00:28<00:01, 35.18it/s] Loading 0: 90%|█████████ | 458/507 [00:31<00:08, 6.09it/s] Loading 0: 91%|█████████ | 461/507 [00:31<00:06, 7.24it/s] Loading 0: 92%|█████████▏| 465/507 [00:31<00:04, 9.07it/s] Loading 0: 93%|█████████▎| 472/507 [00:31<00:02, 13.83it/s] Loading 0: 94%|█████████▍| 476/507 [00:31<00:01, 15.85it/s] Loading 0: 95%|█████████▍| 481/507 [00:31<00:01, 19.36it/s] Loading 0: 96%|█████████▌| 485/507 [00:31<00:01, 21.37it/s] Loading 0: 97%|█████████▋| 490/507 [00:32<00:00, 25.43it/s] Loading 0: 97%|█████████▋| 494/507 [00:32<00:00, 26.05it/s] Loading 0: 98%|█████████▊| 499/507 [00:32<00:00, 29.72it/s] Loading 0: 99%|█████████▉| 503/507 [00:32<00:00, 30.64it/s]
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job chaiml-espresso-ant-2412-3236-v1-mkmlizer completed after 165.77s with status: succeeded
Stopping job with name chaiml-espresso-ant-2412-3236-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.25s
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-espresso-ant-2412-3236-v1
Waiting for inference service chaiml-espresso-ant-2412-3236-v1 to be ready
Inference service chaiml-espresso-ant-2412-3236-v1 ready after 150.71987771987915s
Pipeline stage MKMLDeployer completed in 151.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.898845672607422s
Received healthy response to inference request in 2.5986671447753906s
Received healthy response to inference request in 2.6649422645568848s
Received healthy response to inference request in 2.4124903678894043s
Received healthy response to inference request in 2.4181318283081055s
5 requests
0 failed requests
5th percentile: 2.4136186599731446
10th percentile: 2.414746952056885
20th percentile: 2.417003536224365
30th percentile: 2.4542388916015625
40th percentile: 2.5264530181884766
50th percentile: 2.5986671447753906
60th percentile: 2.625177192687988
70th percentile: 2.651687240600586
80th percentile: 2.7117229461669923
90th percentile: 2.805284309387207
95th percentile: 2.8520649909973144
99th percentile: 2.8894895362854003
mean time: 2.5986154556274412
Pipeline stage StressChecker completed in 14.31s
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 2.12s
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 1.99s
Shutdown handler de-registered
chaiml-espresso-ant-2412_3236_v1 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 3772.24s
Shutdown handler de-registered
chaiml-espresso-ant-2412_3236_v1 status is now inactive due to auto deactivation removed underperforming models
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1