chaiml-espresso-ant-2412_1172

developer_uid: azuruce

submission_id: chaiml-espresso-ant-2412_1172_v1

model_name: chaiml-espresso-ant-2412_1172_v1

model_group: ChaiML/espresso_ant_2412

status: inactive

timestamp: 2024-12-04T17:05:21+00:00

num_battles: 17617

num_wins: 8907

celo_rating: 1265.38

family_friendly_score: 0.5898

family_friendly_standard_error: 0.006956090281185258

submission_type: basic

model_repo: ChaiML/espresso_ant_241204_albert_v1

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.38481341838770616, 'latency_mean': 2.598584222793579, 'latency_p50': 2.5991039276123047, 'latency_p90': 2.837595891952515}, {'batch_size': 3, 'throughput': 0.8195502753074612, 'latency_mean': 3.6468704402446748, 'latency_p50': 3.6745163202285767, 'latency_p90': 3.9686972856521607}, {'batch_size': 5, 'throughput': 1.0890300325417483, 'latency_mean': 4.566528255939484, 'latency_p50': 4.602067589759827, 'latency_p90': 5.001850414276123}, {'batch_size': 6, 'throughput': 1.1788690006014284, 'latency_mean': 5.051678919792176, 'latency_p50': 5.015559792518616, 'latency_p90': 5.637545824050903}, {'batch_size': 10, 'throughput': 1.4045147338496426, 'latency_mean': 7.076299731731415, 'latency_p50': 7.095301628112793, 'latency_p90': 8.073638582229615}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-2412_1172_v1

is_internal_developer: True

language_model: ChaiML/espresso_ant_241204_albert_v1

model_size: 22B

ranking_group: single

throughput_3p7s: 0.84

us_pacific_date: 2024-12-04

win_ratio: 0.5055911903275245

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, '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 chaiml-espresso-ant-2412-1172-v1-mkmlizer
Waiting for job on chaiml-espresso-ant-2412-1172-v1-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
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-1172-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-espresso-ant-2412-1172-v1-mkmlizer: Downloaded to shared memory in 90.671s
chaiml-espresso-ant-2412-1172-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbmk_mt5b, device:0
chaiml-espresso-ant-2412-1172-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-espresso-ant-2412-1172-v1-mkmlizer: quantized model in 43.768s
chaiml-espresso-ant-2412-1172-v1-mkmlizer: Processed model ChaiML/espresso_ant_241204_albert_v1 in 134.439s
chaiml-espresso-ant-2412-1172-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-2412-1172-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-2412-1172-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-2412-1172-v1
chaiml-espresso-ant-2412-1172-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-1172-v1/config.json
chaiml-espresso-ant-2412-1172-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-1172-v1/special_tokens_map.json
chaiml-espresso-ant-2412-1172-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-1172-v1/tokenizer_config.json
chaiml-espresso-ant-2412-1172-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-1172-v1/tokenizer.json
chaiml-espresso-ant-2412-1172-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-2412-1172-v1/flywheel_model.1.safetensors
chaiml-espresso-ant-2412-1172-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-2412-1172-v1/flywheel_model.0.safetensors
chaiml-espresso-ant-2412-1172-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 23.90it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 40.63it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 39.95it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 40.32it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 41.34it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 34.71it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:11, 42.08it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 41.45it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:12, 35.86it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:16, 27.83it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:16, 27.54it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:13, 32.75it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 32.63it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:12, 35.13it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:11, 36.89it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 41.72it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 40.45it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 38.53it/s]
Loading 0:  20%|█▉        | 101/507 [00:02<00:10, 38.33it/s]
Loading 0:  21%|██        | 105/507 [00:02<00:10, 38.38it/s]
Loading 0:  21%|██▏       | 109/507 [00:02<00:10, 36.66it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:14, 27.23it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:14, 26.77it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:13, 27.70it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 34.89it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:11, 33.93it/s]
Loading 0:  27%|██▋       | 138/507 [00:03<00:10, 36.37it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 34.18it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 37.02it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:09, 35.67it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 38.71it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 37.70it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 36.43it/s]
Loading 0:  33%|███▎      | 169/507 [00:04<00:12, 27.19it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:12, 27.73it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:12, 26.08it/s]
Loading 0:  36%|███▌      | 181/507 [00:05<00:11, 28.96it/s]
Loading 0:  36%|███▋      | 185/507 [00:05<00:11, 28.12it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 36.80it/s]
Loading 0:  39%|███▉      | 197/507 [00:05<00:08, 37.62it/s]
Loading 0:  40%|███▉      | 202/507 [00:05<00:07, 38.97it/s]
Loading 0:  41%|████      | 208/507 [00:05<00:07, 39.62it/s]
Loading 0:  42%|████▏     | 213/507 [00:06<00:07, 39.04it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:06, 41.67it/s]
Loading 0:  44%|████▍     | 223/507 [00:06<00:07, 38.27it/s]
Loading 0:  45%|████▍     | 227/507 [00:06<00:08, 32.18it/s]
Loading 0:  46%|████▌     | 231/507 [00:06<00:09, 30.44it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 35.35it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:07, 34.83it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:06, 37.72it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:06, 37.13it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 39.25it/s]
Loading 0:  51%|█████▏    | 260/507 [00:07<00:06, 37.90it/s]
Loading 0:  52%|█████▏    | 265/507 [00:07<00:06, 38.71it/s]
Loading 0:  53%|█████▎    | 269/507 [00:07<00:06, 38.29it/s]
Loading 0:  54%|█████▍    | 274/507 [00:07<00:05, 39.15it/s]
Loading 0:  55%|█████▍    | 278/507 [00:07<00:05, 38.29it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:05, 39.26it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:08, 25.42it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 28.71it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 28.71it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:50,  1.21it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:28,  1.38it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:40,  2.00it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:18,  2.50it/s]
Loading 0:  62%|██████▏   | 314/507 [00:23<00:56,  3.43it/s]
Loading 0:  63%|██████▎   | 319/507 [00:23<00:37,  5.00it/s]
Loading 0:  64%|██████▍   | 324/507 [00:24<00:25,  7.07it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:19,  9.04it/s]
Loading 0:  65%|██████▌   | 332/507 [00:24<00:15, 11.48it/s]
Loading 0:  66%|██████▋   | 337/507 [00:24<00:11, 15.35it/s]
Loading 0:  67%|██████▋   | 341/507 [00:24<00:10, 15.49it/s]
Loading 0:  68%|██████▊   | 345/507 [00:24<00:09, 17.96it/s]
Loading 0:  69%|██████▉   | 349/507 [00:24<00:07, 20.44it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:06, 25.09it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 26.57it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 30.88it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 31.34it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 35.33it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:03, 33.76it/s]
Loading 0:  75%|███████▍  | 380/507 [00:25<00:03, 35.03it/s]
Loading 0:  76%|███████▌  | 384/507 [00:25<00:03, 31.03it/s]
Loading 0:  77%|███████▋  | 389/507 [00:26<00:03, 33.51it/s]
Loading 0:  78%|███████▊  | 393/507 [00:26<00:03, 33.15it/s]
Loading 0:  78%|███████▊  | 397/507 [00:26<00:04, 25.69it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:04, 25.81it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 33.47it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 33.43it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 36.45it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 35.91it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 39.11it/s]
Loading 0:  85%|████████▌ | 431/507 [00:27<00:01, 39.18it/s]
Loading 0:  86%|████████▌ | 436/507 [00:27<00:01, 40.25it/s]
Loading 0:  87%|████████▋ | 441/507 [00:27<00:01, 41.21it/s]
Loading 0:  88%|████████▊ | 446/507 [00:27<00:01, 35.56it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 42.07it/s]
Loading 0:  91%|█████████ | 459/507 [00:30<00:06,  6.94it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.30it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 13.05it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:02, 14.72it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 17.91it/s]
Loading 0:  96%|█████████▌| 485/507 [00:30<00:01, 19.94it/s]
Loading 0:  97%|█████████▋| 490/507 [00:31<00:00, 23.42it/s]
Loading 0:  97%|█████████▋| 494/507 [00:31<00:00, 25.02it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 28.58it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 29.30it/s]
                                                            
Job chaiml-espresso-ant-2412-1172-v1-mkmlizer completed after 165.96s with status: succeeded
Stopping job with name chaiml-espresso-ant-2412-1172-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.46s
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-espresso-ant-2412-1172-v1
Waiting for inference service chaiml-espresso-ant-2412-1172-v1 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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-espresso-ant-2412-1172-v1 ready after 250.80592036247253s
Pipeline stage MKMLDeployer completed in 251.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.943603754043579s
Received healthy response to inference request in 2.2602992057800293s
Received healthy response to inference request in 2.767096519470215s
Received healthy response to inference request in 2.37502121925354s
Received healthy response to inference request in 2.232752799987793s
5 requests
0 failed requests
5th percentile: 2.23826208114624
10th percentile: 2.2437713623046873
20th percentile: 2.254789924621582
30th percentile: 2.2832436084747316
40th percentile: 2.329132413864136
50th percentile: 2.37502121925354
60th percentile: 2.53185133934021
70th percentile: 2.68868145942688
80th percentile: 2.8023979663848877
90th percentile: 2.8730008602142334
95th percentile: 2.9083023071289062
99th percentile: 2.9365434646606445
mean time: 2.5157546997070312
Pipeline stage StressChecker completed in 13.95s
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 2.25s
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 2.40s
Shutdown handler de-registered
chaiml-espresso-ant-2412_1172_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 3185.92s
Shutdown handler de-registered
chaiml-espresso-ant-2412_1172_v1 status is now inactive due to auto deactivation removed underperforming models