developer_uid: azuruce
submission_id: chaiml-espresso-ant-lla_1666_v13
model_name: chaiml-espresso-ant-lla_1666_v13
model_group: ChaiML/espresso_ant_llam
status: torndown
timestamp: 2024-12-05T08:54:42+00:00
num_battles: 10487
num_wins: 5401
celo_rating: 1274.2
family_friendly_score: 0.5816
family_friendly_standard_error: 0.006976266049972578
submission_type: basic
model_repo: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3817549240831685, 'latency_mean': 2.6194202661514283, 'latency_p50': 2.624318480491638, 'latency_p90': 2.9052425146102907}, {'batch_size': 2, 'throughput': 0.6040012890763138, 'latency_mean': 3.307564115524292, 'latency_p50': 3.314868211746216, 'latency_p90': 3.707636094093323}, {'batch_size': 3, 'throughput': 0.7591114521600367, 'latency_mean': 3.9444646418094633, 'latency_p50': 3.920075535774231, 'latency_p90': 4.347867488861084}, {'batch_size': 4, 'throughput': 0.8886772038346257, 'latency_mean': 4.492299817800522, 'latency_p50': 4.482176303863525, 'latency_p90': 4.972115755081177}, {'batch_size': 5, 'throughput': 0.9708584464180695, 'latency_mean': 5.116649857759476, 'latency_p50': 5.124242067337036, 'latency_p90': 5.733686327934264}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-espresso-ant-lla_1666_v13
is_internal_developer: True
language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha
model_size: 22B
ranking_group: single
throughput_3p7s: 0.71
us_pacific_date: 2024-12-05
win_ratio: 0.5150185944502718
generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, '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-lla-1666-v13-mkmlizer
Waiting for job on chaiml-espresso-ant-lla-1666-v13-mkmlizer to finish
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ _____ __ __ ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ /___/ ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ Version: 0.11.12 ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ https://mk1.ai ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ belonging to: ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ Chai Research Corp. ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ║ ║
chaiml-espresso-ant-lla-1666-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-lla-1666-v13-mkmlizer: Downloaded to shared memory in 41.935s
chaiml-espresso-ant-lla-1666-v13-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0bjv083o, device:0
chaiml-espresso-ant-lla-1666-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-lla-1666-v13-mkmlizer: quantized model in 45.279s
chaiml-espresso-ant-lla-1666-v13-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha in 87.215s
chaiml-espresso-ant-lla-1666-v13-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-lla-1666-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-lla-1666-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v13
chaiml-espresso-ant-lla-1666-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v13/config.json
chaiml-espresso-ant-lla-1666-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v13/special_tokens_map.json
chaiml-espresso-ant-lla-1666-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v13/tokenizer_config.json
chaiml-espresso-ant-lla-1666-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v13/tokenizer.json
chaiml-espresso-ant-lla-1666-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v13/flywheel_model.1.safetensors
chaiml-espresso-ant-lla-1666-v13-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 5/507 [00:00<00:21, 23.81it/s] Loading 0: 2%|▏ | 10/507 [00:00<00:14, 33.69it/s] Loading 0: 3%|▎ | 14/507 [00:00<00:17, 28.92it/s] Loading 0: 4%|▎ | 19/507 [00:00<00:14, 34.49it/s] Loading 0: 5%|▍ | 23/507 [00:00<00:15, 30.38it/s] Loading 0: 6%|▌ | 28/507 [00:00<00:13, 34.57it/s] Loading 0: 6%|▋ | 32/507 [00:01<00:15, 30.52it/s] Loading 0: 7%|▋ | 37/507 [00:01<00:13, 35.02it/s] Loading 0: 8%|▊ | 41/507 [00:01<00:14, 31.68it/s] Loading 0: 9%|▉ | 47/507 [00:01<00:12, 36.47it/s] Loading 0: 10%|█ | 51/507 [00:01<00:13, 33.92it/s] Loading 0: 11%|█ | 55/507 [00:01<00:18, 23.87it/s] Loading 0: 11%|█▏ | 58/507 [00:01<00:18, 24.94it/s] Loading 0: 12%|█▏ | 63/507 [00:02<00:15, 29.34it/s] Loading 0: 13%|█▎ | 67/507 [00:02<00:14, 29.38it/s] Loading 0: 14%|█▍ | 71/507 [00:02<00:13, 31.73it/s] Loading 0: 15%|█▍ | 75/507 [00:02<00:12, 33.54it/s] Loading 0: 16%|█▌ | 80/507 [00:02<00:12, 33.00it/s] Loading 0: 17%|█▋ | 87/507 [00:02<00:10, 39.32it/s] Loading 0: 18%|█▊ | 92/507 [00:02<00:11, 37.57it/s] Loading 0: 19%|█▉ | 96/507 [00:02<00:11, 35.73it/s] Loading 0: 20%|█▉ | 100/507 [00:03<00:12, 33.59it/s] Loading 0: 21%|██ | 105/507 [00:03<00:11, 35.27it/s] Loading 0: 21%|██▏ | 109/507 [00:03<00:12, 33.08it/s] Loading 0: 22%|██▏ | 113/507 [00:03<00:16, 23.44it/s] Loading 0: 23%|██▎ | 116/507 [00:03<00:17, 21.92it/s] Loading 0: 24%|██▍ | 122/507 [00:04<00:15, 24.95it/s] Loading 0: 25%|██▌ | 127/507 [00:04<00:12, 29.53it/s] Loading 0: 26%|██▌ | 131/507 [00:04<00:13, 27.63it/s] Loading 0: 27%|██▋ | 136/507 [00:04<00:11, 31.68it/s] Loading 0: 28%|██▊ | 140/507 [00:04<00:12, 29.30it/s] Loading 0: 29%|██▊ | 145/507 [00:04<00:10, 33.49it/s] Loading 0: 29%|██▉ | 149/507 [00:04<00:12, 29.77it/s] Loading 0: 31%|███ | 156/507 [00:04<00:09, 36.66it/s] Loading 0: 32%|███▏ | 160/507 [00:05<00:09, 35.52it/s] Loading 0: 32%|███▏ | 164/507 [00:05<00:09, 35.53it/s] Loading 0: 33%|███▎ | 169/507 [00:05<00:12, 27.73it/s] Loading 0: 34%|███▍ | 173/507 [00:05<00:11, 28.72it/s] Loading 0: 35%|███▍ | 177/507 [00:05<00:11, 27.60it/s] Loading 0: 36%|███▌ | 181/507 [00:05<00:10, 30.12it/s] Loading 0: 36%|███▋ | 185/507 [00:06<00:11, 28.80it/s] Loading 0: 38%|███▊ | 192/507 [00:06<00:08, 36.08it/s] Loading 0: 39%|███▊ | 196/507 [00:06<00:09, 33.86it/s] Loading 0: 40%|███▉ | 201/507 [00:06<00:08, 36.14it/s] Loading 0: 40%|████ | 205/507 [00:06<00:08, 34.35it/s] Loading 0: 41%|████▏ | 210/507 [00:06<00:08, 36.28it/s] Loading 0: 42%|████▏ | 214/507 [00:06<00:08, 35.01it/s] Loading 0: 43%|████▎ | 218/507 [00:06<00:08, 35.29it/s] Loading 0: 44%|████▍ | 222/507 [00:07<00:08, 34.24it/s] Loading 0: 45%|████▍ | 226/507 [00:07<00:11, 24.77it/s] Loading 0: 45%|████▌ | 230/507 [00:07<00:11, 25.06it/s] Loading 0: 47%|████▋ | 237/507 [00:07<00:08, 32.19it/s] Loading 0: 48%|████▊ | 241/507 [00:07<00:08, 31.20it/s] Loading 0: 49%|████▊ | 246/507 [00:07<00:07, 33.12it/s] Loading 0: 49%|████▉ | 250/507 [00:07<00:08, 32.11it/s] Loading 0: 50%|█████ | 254/507 [00:08<00:07, 33.24it/s] Loading 0: 51%|█████ | 258/507 [00:08<00:08, 29.36it/s] Loading 0: 52%|█████▏ | 264/507 [00:08<00:07, 33.81it/s] Loading 0: 53%|█████▎ | 268/507 [00:08<00:07, 31.87it/s] Loading 0: 54%|█████▍ | 273/507 [00:08<00:06, 33.95it/s] Loading 0: 55%|█████▍ | 277/507 [00:08<00:07, 32.25it/s] Loading 0: 56%|█████▌ | 282/507 [00:08<00:06, 36.13it/s] Loading 0: 56%|█████▋ | 286/507 [00:09<00:09, 23.59it/s] Loading 0: 57%|█████▋ | 289/507 [00:09<00:09, 23.45it/s] Loading 0: 58%|█████▊ | 293/507 [00:09<00:08, 23.97it/s] Loading 0: 59%|█████▉ | 299/507 [00:20<00:08, 23.97it/s] Loading 0: 59%|█████▉ | 300/507 [00:24<03:17, 1.05it/s] Loading 0: 60%|█████▉ | 302/507 [00:24<02:49, 1.21it/s] Loading 0: 61%|██████ | 307/507 [00:25<01:50, 1.81it/s] Loading 0: 61%|██████ | 310/507 [00:25<01:25, 2.30it/s] Loading 0: 62%|██████▏ | 313/507 [00:25<01:05, 2.96it/s] Loading 0: 62%|██████▏ | 316/507 [00:25<00:49, 3.86it/s] Loading 0: 63%|██████▎ | 320/507 [00:25<00:35, 5.32it/s] Loading 0: 64%|██████▍ | 325/507 [00:25<00:22, 7.93it/s] Loading 0: 65%|██████▍ | 329/507 [00:25<00:18, 9.82it/s] Loading 0: 66%|██████▌ | 334/507 [00:26<00:13, 13.30it/s] Loading 0: 67%|██████▋ | 339/507 [00:26<00:10, 16.75it/s] Loading 0: 68%|██████▊ | 343/507 [00:26<00:11, 14.83it/s] Loading 0: 68%|██████▊ | 347/507 [00:26<00:09, 16.45it/s] Loading 0: 70%|██████▉ | 354/507 [00:26<00:06, 23.08it/s] Loading 0: 71%|███████ | 358/507 [00:26<00:06, 24.81it/s] Loading 0: 72%|███████▏ | 363/507 [00:27<00:05, 28.78it/s] Loading 0: 72%|███████▏ | 367/507 [00:27<00:04, 29.11it/s] Loading 0: 73%|███████▎ | 372/507 [00:27<00:04, 33.02it/s] Loading 0: 74%|███████▍ | 376/507 [00:27<00:03, 33.67it/s] Loading 0: 75%|███████▌ | 381/507 [00:27<00:03, 37.53it/s] Loading 0: 76%|███████▌ | 386/507 [00:27<00:03, 38.50it/s] Loading 0: 77%|███████▋ | 391/507 [00:27<00:03, 34.33it/s] Loading 0: 78%|███████▊ | 395/507 [00:28<00:04, 26.68it/s] Loading 0: 79%|███████▉ | 401/507 [00:28<00:03, 28.29it/s] Loading 0: 80%|████████ | 408/507 [00:28<00:02, 34.63it/s] Loading 0: 81%|████████▏ | 412/507 [00:28<00:02, 33.27it/s] Loading 0: 82%|████████▏ | 417/507 [00:28<00:02, 36.40it/s] Loading 0: 83%|████████▎ | 421/507 [00:28<00:02, 36.22it/s] Loading 0: 84%|████████▍ | 426/507 [00:28<00:02, 39.22it/s] Loading 0: 85%|████████▌ | 431/507 [00:29<00:01, 38.94it/s] Loading 0: 86%|████████▌ | 436/507 [00:29<00:01, 39.79it/s] Loading 0: 87%|████████▋ | 441/507 [00:29<00:01, 41.69it/s] Loading 0: 88%|████████▊ | 446/507 [00:29<00:01, 33.05it/s] Loading 0: 89%|████████▉ | 452/507 [00:29<00:01, 39.01it/s] Loading 0: 90%|█████████ | 457/507 [00:31<00:07, 6.59it/s] Loading 0: 91%|█████████ | 461/507 [00:32<00:05, 8.15it/s] Loading 0: 92%|█████████▏| 465/507 [00:32<00:04, 10.07it/s] Loading 0: 93%|█████████▎| 472/507 [00:32<00:02, 15.06it/s] Loading 0: 94%|█████████▍| 476/507 [00:32<00:01, 17.40it/s] Loading 0: 95%|█████████▍| 481/507 [00:32<00:01, 21.52it/s] Loading 0: 96%|█████████▌| 486/507 [00:32<00:00, 24.84it/s] Loading 0: 97%|█████████▋| 490/507 [00:32<00:00, 27.47it/s] Loading 0: 97%|█████████▋| 494/507 [00:32<00:00, 28.60it/s] Loading 0: 98%|█████████▊| 499/507 [00:32<00:00, 31.80it/s] Loading 0: 99%|█████████▉| 503/507 [00:33<00:00, 31.98it/s]
Job chaiml-espresso-ant-lla-1666-v13-mkmlizer completed after 121.93s with status: succeeded
Stopping job with name chaiml-espresso-ant-lla-1666-v13-mkmlizer
Pipeline stage MKMLizer completed in 123.70s
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 chaiml-espresso-ant-lla-1666-v13
Waiting for inference service chaiml-espresso-ant-lla-1666-v13 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
Inference service chaiml-espresso-ant-lla-1666-v13 ready after 164.266863822937s
Pipeline stage MKMLDeployer completed in 165.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8112947940826416s
Received healthy response to inference request in 2.3843231201171875s
Received healthy response to inference request in 2.5009517669677734s
Received healthy response to inference request in 2.291503429412842s
Received healthy response to inference request in 2.3126749992370605s
5 requests
0 failed requests
5th percentile: 2.2957377433776855
10th percentile: 2.2999720573425293
20th percentile: 2.308440685272217
30th percentile: 2.327004623413086
40th percentile: 2.355663871765137
50th percentile: 2.3843231201171875
60th percentile: 2.430974578857422
70th percentile: 2.4776260375976564
80th percentile: 2.563020372390747
90th percentile: 2.6871575832366945
95th percentile: 2.749226188659668
99th percentile: 2.798881072998047
mean time: 2.460149621963501
Pipeline stage StressChecker completed in 14.22s
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 2.47s
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 2.45s
Shutdown handler de-registered
chaiml-espresso-ant-lla_1666_v13 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-espresso-ant-lla-1666-v13-profiler
Waiting for inference service chaiml-espresso-ant-lla-1666-v13-profiler to be ready
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 3999.17s
Shutdown handler de-registered
chaiml-espresso-ant-lla_1666_v13 status is now inactive due to auto deactivation removed underperforming models
chaiml-espresso-ant-lla_1666_v13 status is now torndown due to DeploymentManager action
chaiml-espresso-ant-lla_1666_v13 status is now torndown due to DeploymentManager action
chaiml-espresso-ant-lla_1666_v13 status is now torndown due to DeploymentManager action