chaiml-espresso-ant-lla_1666

developer_uid: azuruce

submission_id: chaiml-espresso-ant-lla_1666_v10

model_name: chaiml-espresso-ant-lla_1666_v10

model_group: ChaiML/espresso_ant_llam

status: inactive

timestamp: 2024-12-05T08:53:35+00:00

num_battles: 9830

num_wins: 4849

celo_rating: 1260.12

family_friendly_score: 0.5871999999999999

family_friendly_standard_error: 0.006962702923434261

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: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3863226097162269, 'latency_mean': 2.5884307050704956, 'latency_p50': 2.6042845249176025, 'latency_p90': 2.8330003023147583}, {'batch_size': 3, 'throughput': 0.8270828490957142, 'latency_mean': 3.613403763771057, 'latency_p50': 3.588026523590088, 'latency_p90': 4.019846892356872}, {'batch_size': 5, 'throughput': 1.095257067860339, 'latency_mean': 4.541423612833023, 'latency_p50': 4.556480288505554, 'latency_p90': 4.977081704139709}, {'batch_size': 6, 'throughput': 1.1782809008735062, 'latency_mean': 5.0438125658035275, 'latency_p50': 5.073545694351196, 'latency_p90': 5.617282056808472}, {'batch_size': 10, 'throughput': 1.400209222298674, 'latency_mean': 7.081056177616119, 'latency_p50': 7.120435476303101, 'latency_p90': 7.923825263977051}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-lla_1666_v10

is_internal_developer: True

language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.86

us_pacific_date: 2024-12-05

win_ratio: 0.4932858596134283

generation_params: {'temperature': 0.77, '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-lla-1666-v10-mkmlizer
Waiting for job on chaiml-espresso-ant-lla-1666-v10-mkmlizer to finish
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-1666-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-lla-1666-v10-mkmlizer: Downloaded to shared memory in 44.276s
chaiml-espresso-ant-lla-1666-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcf9ys3zb, device:0
chaiml-espresso-ant-lla-1666-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-lla-1666-v10-mkmlizer: quantized model in 45.973s
chaiml-espresso-ant-lla-1666-v10-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha in 90.249s
chaiml-espresso-ant-lla-1666-v10-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-lla-1666-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-lla-1666-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v10
chaiml-espresso-ant-lla-1666-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v10/config.json
chaiml-espresso-ant-lla-1666-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v10/special_tokens_map.json
chaiml-espresso-ant-lla-1666-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v10/tokenizer_config.json
chaiml-espresso-ant-lla-1666-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v10/tokenizer.json
chaiml-espresso-ant-lla-1666-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v10/flywheel_model.1.safetensors
chaiml-espresso-ant-lla-1666-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v10/flywheel_model.0.safetensors
chaiml-espresso-ant-lla-1666-v10-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 23.04it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:15, 31.86it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:18, 26.74it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:15, 31.62it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:16, 28.69it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:13, 36.41it/s]
Loading 0:   7%|▋         | 34/507 [00:01<00:13, 35.51it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:12, 38.83it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 39.63it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:13, 34.79it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:17, 25.42it/s]
Loading 0:  11%|█         | 56/507 [00:01<00:19, 22.91it/s]
Loading 0:  12%|█▏        | 61/507 [00:02<00:16, 27.13it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:17, 24.71it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:15, 28.56it/s]
Loading 0:  15%|█▍        | 74/507 [00:02<00:13, 30.98it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:13, 30.54it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:12, 33.68it/s]
Loading 0:  18%|█▊        | 89/507 [00:02<00:14, 29.18it/s]
Loading 0:  19%|█▊        | 94/507 [00:03<00:13, 31.76it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:14, 27.38it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:13, 30.78it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:14, 27.83it/s]
Loading 0:  22%|██▏       | 112/507 [00:03<00:12, 30.92it/s]
Loading 0:  23%|██▎       | 116/507 [00:04<00:20, 19.30it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:17, 22.27it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:14, 26.04it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:15, 24.58it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:13, 27.90it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:14, 25.97it/s]
Loading 0:  29%|██▊       | 145/507 [00:05<00:12, 29.78it/s]
Loading 0:  29%|██▉       | 149/507 [00:05<00:12, 28.60it/s]
Loading 0:  31%|███       | 156/507 [00:05<00:09, 36.51it/s]
Loading 0:  32%|███▏      | 161/507 [00:05<00:09, 37.26it/s]
Loading 0:  33%|███▎      | 166/507 [00:05<00:08, 39.80it/s]
Loading 0:  34%|███▎      | 171/507 [00:05<00:13, 25.27it/s]
Loading 0:  35%|███▍      | 176/507 [00:06<00:12, 25.59it/s]
Loading 0:  36%|███▌      | 181/507 [00:06<00:11, 28.80it/s]
Loading 0:  36%|███▋      | 185/507 [00:06<00:12, 26.74it/s]
Loading 0:  37%|███▋      | 190/507 [00:06<00:10, 29.50it/s]
Loading 0:  38%|███▊      | 194/507 [00:06<00:11, 26.65it/s]
Loading 0:  39%|███▉      | 199/507 [00:06<00:10, 30.34it/s]
Loading 0:  40%|████      | 203/507 [00:07<00:10, 28.15it/s]
Loading 0:  41%|████      | 208/507 [00:07<00:09, 32.12it/s]
Loading 0:  42%|████▏     | 212/507 [00:07<00:10, 28.34it/s]
Loading 0:  43%|████▎     | 217/507 [00:07<00:09, 31.28it/s]
Loading 0:  44%|████▎     | 221/507 [00:07<00:10, 28.33it/s]
Loading 0:  44%|████▍     | 225/507 [00:07<00:13, 20.50it/s]
Loading 0:  45%|████▌     | 230/507 [00:08<00:12, 22.10it/s]
Loading 0:  46%|████▋     | 235/507 [00:08<00:10, 25.45it/s]
Loading 0:  47%|████▋     | 239/507 [00:08<00:11, 24.03it/s]
Loading 0:  48%|████▊     | 244/507 [00:08<00:09, 27.79it/s]
Loading 0:  49%|████▉     | 248/507 [00:08<00:10, 25.68it/s]
Loading 0:  50%|████▉     | 253/507 [00:08<00:08, 29.43it/s]
Loading 0:  51%|█████     | 257/507 [00:09<00:09, 26.31it/s]
Loading 0:  52%|█████▏    | 262/507 [00:09<00:08, 29.75it/s]
Loading 0:  52%|█████▏    | 266/507 [00:09<00:08, 26.92it/s]
Loading 0:  53%|█████▎    | 271/507 [00:09<00:07, 31.32it/s]
Loading 0:  54%|█████▍    | 275/507 [00:09<00:07, 29.53it/s]
Loading 0:  56%|█████▌    | 282/507 [00:09<00:05, 38.35it/s]
Loading 0:  57%|█████▋    | 287/507 [00:10<00:09, 24.44it/s]
Loading 0:  58%|█████▊    | 293/507 [00:10<00:07, 26.93it/s]
Loading 0:  59%|█████▉    | 299/507 [00:25<00:07, 26.93it/s]
Loading 0:  59%|█████▉    | 300/507 [00:25<02:40,  1.29it/s]
Loading 0:  60%|█████▉    | 302/507 [00:25<02:20,  1.45it/s]
Loading 0:  61%|██████    | 307/507 [00:25<01:36,  2.07it/s]
Loading 0:  61%|██████    | 310/507 [00:25<01:17,  2.55it/s]
Loading 0:  62%|██████▏   | 313/507 [00:25<00:59,  3.24it/s]
Loading 0:  63%|██████▎   | 318/507 [00:25<00:39,  4.83it/s]
Loading 0:  64%|██████▎   | 322/507 [00:25<00:29,  6.38it/s]
Loading 0:  64%|██████▍   | 327/507 [00:26<00:19,  9.00it/s]
Loading 0:  65%|██████▌   | 331/507 [00:26<00:15, 11.17it/s]
Loading 0:  66%|██████▌   | 335/507 [00:26<00:12, 13.85it/s]
Loading 0:  67%|██████▋   | 340/507 [00:26<00:10, 15.29it/s]
Loading 0:  68%|██████▊   | 343/507 [00:26<00:09, 16.58it/s]
Loading 0:  68%|██████▊   | 347/507 [00:26<00:08, 18.21it/s]
Loading 0:  70%|██████▉   | 354/507 [00:26<00:05, 25.82it/s]
Loading 0:  71%|███████   | 358/507 [00:27<00:05, 26.81it/s]
Loading 0:  72%|███████▏  | 363/507 [00:27<00:04, 30.73it/s]
Loading 0:  72%|███████▏  | 367/507 [00:27<00:04, 30.56it/s]
Loading 0:  73%|███████▎  | 372/507 [00:27<00:03, 34.03it/s]
Loading 0:  74%|███████▍  | 376/507 [00:27<00:03, 34.10it/s]
Loading 0:  75%|███████▌  | 381/507 [00:27<00:03, 37.41it/s]
Loading 0:  76%|███████▌  | 385/507 [00:27<00:03, 36.13it/s]
Loading 0:  77%|███████▋  | 389/507 [00:27<00:03, 36.42it/s]
Loading 0:  78%|███████▊  | 393/507 [00:27<00:03, 35.17it/s]
Loading 0:  78%|███████▊  | 397/507 [00:28<00:04, 26.00it/s]
Loading 0:  79%|███████▉  | 401/507 [00:28<00:04, 25.89it/s]
Loading 0:  80%|████████  | 408/507 [00:28<00:02, 33.59it/s]
Loading 0:  81%|████████▏ | 412/507 [00:28<00:02, 33.37it/s]
Loading 0:  82%|████████▏ | 417/507 [00:28<00:02, 36.07it/s]
Loading 0:  83%|████████▎ | 421/507 [00:28<00:02, 35.02it/s]
Loading 0:  84%|████████▍ | 426/507 [00:29<00:02, 37.76it/s]
Loading 0:  85%|████████▍ | 430/507 [00:29<00:02, 36.11it/s]
Loading 0:  86%|████████▌ | 435/507 [00:29<00:01, 38.84it/s]
Loading 0:  87%|████████▋ | 439/507 [00:29<00:01, 37.42it/s]
Loading 0:  88%|████████▊ | 444/507 [00:29<00:01, 40.28it/s]
Loading 0:  89%|████████▊ | 449/507 [00:29<00:01, 39.90it/s]
Loading 0:  90%|████████▉ | 454/507 [00:29<00:01, 39.77it/s]
Loading 0:  91%|█████████ | 459/507 [00:32<00:07,  6.29it/s]
Loading 0:  92%|█████████▏| 465/507 [00:32<00:04,  8.80it/s]
Loading 0:  93%|█████████▎| 472/507 [00:32<00:02, 12.74it/s]
Loading 0:  94%|█████████▍| 476/507 [00:32<00:02, 14.83it/s]
Loading 0:  95%|█████████▍| 481/507 [00:32<00:01, 18.39it/s]
Loading 0:  96%|█████████▌| 485/507 [00:32<00:01, 20.44it/s]
Loading 0:  97%|█████████▋| 490/507 [00:32<00:00, 24.17it/s]
Loading 0:  97%|█████████▋| 494/507 [00:32<00:00, 25.81it/s]
Loading 0:  98%|█████████▊| 499/507 [00:33<00:00, 29.20it/s]
Loading 0:  99%|█████████▉| 503/507 [00:33<00:00, 28.87it/s]
Loading 0: 100%|██████████| 507/507 [00:33<00:00, 31.22it/s]
                                                            
Job chaiml-espresso-ant-lla-1666-v10-mkmlizer completed after 121.77s with status: succeeded
Stopping job with name chaiml-espresso-ant-lla-1666-v10-mkmlizer
Pipeline stage MKMLizer completed in 123.17s
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-lla-1666-v10
Waiting for inference service chaiml-espresso-ant-lla-1666-v10 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 chaiml-espresso-ant-lla-1666-v10 ready after 175.66604208946228s
Pipeline stage MKMLDeployer completed in 177.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.241931676864624s
Received healthy response to inference request in 2.4351212978363037s
Received healthy response to inference request in 2.33851957321167s
Received healthy response to inference request in 2.5530388355255127s
Received healthy response to inference request in 2.2196497917175293s
5 requests
0 failed requests
5th percentile: 2.2434237480163572
10th percentile: 2.2671977043151856
20th percentile: 2.314745616912842
30th percentile: 2.3578399181365968
40th percentile: 2.39648060798645
50th percentile: 2.4351212978363037
60th percentile: 2.4822883129119875
70th percentile: 2.529455327987671
80th percentile: 2.6908174037933352
90th percentile: 2.9663745403289794
95th percentile: 3.1041531085968015
99th percentile: 3.2143759632110593
mean time: 2.557652235031128
Pipeline stage StressChecker completed in 14.06s
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 2.17s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
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
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.05s
Shutdown handler de-registered
chaiml-espresso-ant-lla_1666_v10 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 3147.24s
Shutdown handler de-registered
chaiml-espresso-ant-lla_1666_v10 status is now inactive due to auto deactivation removed underperforming models