chaiml-small-espresso-a_6112

developer_uid: azuruce

submission_id: chaiml-small-espresso-a_6112_v11

model_name: chaiml-small-espresso-a_6112_v11

model_group: ChaiML/small_espresso_an

status: inactive

timestamp: 2024-12-06T18:33:08+00:00

num_battles: 9299

num_wins: 4648

celo_rating: 1264.12

family_friendly_score: 0.5778

family_friendly_standard_error: 0.006984943235273999

submission_type: basic

model_repo: ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.38709621342195416, 'latency_mean': 2.583273100852966, 'latency_p50': 2.5945942401885986, 'latency_p90': 2.87599892616272}, {'batch_size': 3, 'throughput': 0.8183372894898081, 'latency_mean': 3.6450152373313904, 'latency_p50': 3.6269253492355347, 'latency_p90': 4.019462299346924}, {'batch_size': 5, 'throughput': 1.0807621380558126, 'latency_mean': 4.602554416656494, 'latency_p50': 4.606431841850281, 'latency_p90': 5.151516914367676}, {'batch_size': 6, 'throughput': 1.1678014626811437, 'latency_mean': 5.106157759428024, 'latency_p50': 5.1272196769714355, 'latency_p90': 5.7939934730529785}, {'batch_size': 10, 'throughput': 1.385516291674715, 'latency_mean': 7.13420880317688, 'latency_p50': 7.069091200828552, 'latency_p90': 7.969595265388489}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-small-espresso-a_6112_v11

is_internal_developer: True

language_model: ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a

model_size: 22B

ranking_group: single

throughput_3p7s: 0.84

us_pacific_date: 2024-12-06

win_ratio: 0.4998386923325089

generation_params: {'temperature': 1.0, '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-small-espresso-a-6112-v11-mkmlizer
Waiting for job on chaiml-small-espresso-a-6112-v11-mkmlizer to finish
chaiml-small-espresso-a-6112-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-espresso-a-6112-v11-mkmlizer: ║     _____            __           __                                ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║       /___/                                                         ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║                                                                     ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║                                                                     ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║                                                                     ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ║                                                                     ║
chaiml-small-espresso-a-6112-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-small-espresso-a-6112-v11-mkmlizer: Downloaded to shared memory in 60.684s
chaiml-small-espresso-a-6112-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpthzbspop, device:0
chaiml-small-espresso-a-6112-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-small-espresso-a-6112-v11-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-espresso-a-6112-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-espresso-a-6112-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v11
chaiml-small-espresso-a-6112-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v11/config.json
chaiml-small-espresso-a-6112-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v11/special_tokens_map.json
chaiml-small-espresso-a-6112-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v11/tokenizer_config.json
chaiml-small-espresso-a-6112-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v11/tokenizer.json
chaiml-small-espresso-a-6112-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v11/flywheel_model.1.safetensors
chaiml-small-espresso-a-6112-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v11/flywheel_model.0.safetensors
chaiml-small-espresso-a-6112-v11-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 24.72it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 40.78it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 37.95it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 37.62it/s]
Loading 0:   5%|▌         | 26/507 [00:00<00:13, 36.43it/s]
Loading 0:   6%|▌         | 31/507 [00:00<00:12, 37.65it/s]
Loading 0:   7%|▋         | 35/507 [00:00<00:12, 37.50it/s]
Loading 0:   8%|▊         | 40/507 [00:01<00:12, 38.26it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 38.62it/s]
Loading 0:   9%|▉         | 48/507 [00:01<00:14, 30.63it/s]
Loading 0:  10%|█         | 52/507 [00:01<00:14, 32.23it/s]
Loading 0:  11%|█         | 56/507 [00:01<00:22, 20.49it/s]
Loading 0:  12%|█▏        | 61/507 [00:01<00:17, 25.46it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:17, 25.00it/s]
Loading 0:  14%|█▍        | 71/507 [00:02<00:13, 31.87it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:11, 38.33it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:11, 37.33it/s]
Loading 0:  17%|█▋        | 88/507 [00:02<00:11, 37.89it/s]
Loading 0:  18%|█▊        | 93/507 [00:02<00:10, 39.12it/s]
Loading 0:  19%|█▉        | 98/507 [00:02<00:12, 32.80it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:10, 38.56it/s]
Loading 0:  22%|██▏       | 110/507 [00:03<00:10, 36.20it/s]
Loading 0:  22%|██▏       | 114/507 [00:03<00:15, 25.92it/s]
Loading 0:  23%|██▎       | 118/507 [00:03<00:14, 26.22it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 26.19it/s]
Loading 0:  25%|██▌       | 127/507 [00:03<00:12, 30.75it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:13, 28.19it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 35.45it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 34.25it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 36.76it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:10, 34.90it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 37.09it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 36.46it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 37.18it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:11, 28.24it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 29.31it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 28.47it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.30it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 33.68it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 36.39it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:09, 33.06it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 35.41it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 34.88it/s]
Loading 0:  42%|████▏     | 211/507 [00:06<00:07, 38.56it/s]
Loading 0:  43%|████▎     | 217/507 [00:06<00:07, 39.04it/s]
Loading 0:  44%|████▎     | 221/507 [00:06<00:07, 35.75it/s]
Loading 0:  44%|████▍     | 225/507 [00:06<00:10, 26.97it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:09, 28.61it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:07, 35.88it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:07, 35.78it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:06, 38.31it/s]
Loading 0:  50%|████▉     | 251/507 [00:07<00:06, 38.37it/s]
Loading 0:  50%|█████     | 256/507 [00:07<00:06, 39.15it/s]
Loading 0:  51%|█████▏    | 261/507 [00:07<00:05, 41.25it/s]
Loading 0:  52%|█████▏    | 266/507 [00:07<00:06, 35.71it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:05, 42.43it/s]
Loading 0:  55%|█████▍    | 278/507 [00:08<00:05, 42.15it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:05, 42.44it/s]
Loading 0:  57%|█████▋    | 288/507 [00:08<00:07, 28.71it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 29.74it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:06, 29.74it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:43,  1.27it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:22,  1.44it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:36,  2.07it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:17,  2.56it/s]
Loading 0:  62%|██████▏   | 314/507 [00:23<00:55,  3.50it/s]
Loading 0:  63%|██████▎   | 319/507 [00:23<00:36,  5.09it/s]
Loading 0:  64%|██████▍   | 324/507 [00:24<00:25,  7.20it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:19,  9.25it/s]
Loading 0:  65%|██████▌   | 332/507 [00:24<00:14, 11.78it/s]
Loading 0:  67%|██████▋   | 338/507 [00:24<00:10, 16.70it/s]
Loading 0:  68%|██████▊   | 343/507 [00:24<00:10, 15.79it/s]
Loading 0:  68%|██████▊   | 347/507 [00:24<00:09, 17.53it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:06, 24.46it/s]
Loading 0:  71%|███████   | 359/507 [00:25<00:05, 27.12it/s]
Loading 0:  72%|███████▏  | 364/507 [00:25<00:04, 29.94it/s]
Loading 0:  73%|███████▎  | 368/507 [00:25<00:04, 31.25it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:04, 33.12it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:03, 33.44it/s]
Loading 0:  75%|███████▌  | 381/507 [00:25<00:03, 37.28it/s]
Loading 0:  76%|███████▌  | 386/507 [00:25<00:03, 38.41it/s]
Loading 0:  77%|███████▋  | 391/507 [00:26<00:03, 33.98it/s]
Loading 0:  78%|███████▊  | 395/507 [00:26<00:04, 27.14it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 28.94it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 35.71it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 35.12it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 37.49it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 35.61it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 38.85it/s]
Loading 0:  85%|████████▌ | 431/507 [00:27<00:01, 38.90it/s]
Loading 0:  86%|████████▌ | 436/507 [00:27<00:01, 39.17it/s]
Loading 0:  87%|████████▋ | 441/507 [00:27<00:01, 40.40it/s]
Loading 0:  88%|████████▊ | 446/507 [00:27<00:01, 35.03it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 40.61it/s]
Loading 0:  91%|█████████ | 459/507 [00:30<00:06,  7.03it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.47it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 13.34it/s]
Loading 0:  94%|█████████▍| 477/507 [00:30<00:01, 16.01it/s]
Loading 0:  95%|█████████▌| 482/507 [00:30<00:01, 19.32it/s]
Loading 0:  96%|█████████▌| 487/507 [00:30<00:00, 22.99it/s]
Loading 0:  97%|█████████▋| 492/507 [00:30<00:00, 23.76it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 30.09it/s]
Loading 0:  99%|█████████▉| 504/507 [00:31<00:00, 32.09it/s]
                                                            
Job chaiml-small-espresso-a-6112-v11-mkmlizer completed after 135.36s with status: succeeded
Stopping job with name chaiml-small-espresso-a-6112-v11-mkmlizer
Pipeline stage MKMLizer completed in 135.85s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-small-espresso-a-6112-v11
Waiting for inference service chaiml-small-espresso-a-6112-v11 to be ready
Inference service chaiml-small-espresso-a-6112-v11 ready after 160.5613293647766s
Pipeline stage MKMLDeployer completed in 161.13s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.7387828826904297s
Received healthy response to inference request in 2.2870259284973145s
Received healthy response to inference request in 2.925089120864868s
Received healthy response to inference request in 2.3617024421691895s
5 requests
1 failed requests
5th percentile: 2.3019612312316893
10th percentile: 2.3168965339660645
20th percentile: 2.3467671394348146
30th percentile: 2.4371185302734375
40th percentile: 2.5879507064819336
50th percentile: 2.7387828826904297
60th percentile: 2.813305377960205
70th percentile: 2.8878278732299805
80th percentile: 6.403829717636111
90th percentile: 13.361310911178592
95th percentile: 16.840051507949827
99th percentile: 19.62304398536682
mean time: 6.126278495788574
%s, retrying in %s seconds...
Received healthy response to inference request in 2.68833327293396s
Received healthy response to inference request in 2.773090124130249s
Received healthy response to inference request in 2.4247348308563232s
Received healthy response to inference request in 2.3718740940093994s
Received healthy response to inference request in 2.253277540206909s
5 requests
0 failed requests
5th percentile: 2.2769968509674072
10th percentile: 2.3007161617279053
20th percentile: 2.3481547832489014
30th percentile: 2.3824462413787844
40th percentile: 2.403590536117554
50th percentile: 2.4247348308563232
60th percentile: 2.530174207687378
70th percentile: 2.6356135845184325
80th percentile: 2.7052846431732176
90th percentile: 2.7391873836517333
95th percentile: 2.7561387538909914
99th percentile: 2.7696998500823975
mean time: 2.5022619724273683
Pipeline stage StressChecker completed in 45.63s
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 2.18s
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 2.11s
Shutdown handler de-registered
chaiml-small-espresso-a_6112_v11 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 3122.37s
Shutdown handler de-registered
chaiml-small-espresso-a_6112_v11 status is now inactive due to auto deactivation removed underperforming models