chaiml-small-anthropic-r_8708

developer_uid: azuruce

submission_id: chaiml-small-anthropic-r_8708_v1

model_name: anthropic200

model_group: ChaiML/small_anthropic_r

status: inactive

timestamp: 2024-11-19T21:12:08+00:00

num_battles: 9889

num_wins: 4977

celo_rating: 1257.44

family_friendly_score: 0.5804

family_friendly_standard_error: 0.006979052084631551

submission_type: basic

model_repo: ChaiML/small_anthropic_rerun_sample200

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3850266616434396, 'latency_mean': 2.5971269631385803, 'latency_p50': 2.6084673404693604, 'latency_p90': 2.839107394218445}, {'batch_size': 3, 'throughput': 0.8166731105143973, 'latency_mean': 3.663306177854538, 'latency_p50': 3.672263741493225, 'latency_p90': 3.9983288526535032}, {'batch_size': 5, 'throughput': 1.075405224323238, 'latency_mean': 4.627142214775086, 'latency_p50': 4.652501940727234, 'latency_p90': 5.112771916389465}, {'batch_size': 6, 'throughput': 1.1521827959735822, 'latency_mean': 5.1584708893299105, 'latency_p50': 5.15201723575592, 'latency_p90': 5.798868465423584}, {'batch_size': 10, 'throughput': 1.3686416904790286, 'latency_mean': 7.264587678909302, 'latency_p50': 7.26010799407959, 'latency_p90': 8.305022764205933}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: anthropic200

is_internal_developer: True

language_model: ChaiML/small_anthropic_rerun_sample200

model_size: 22B

ranking_group: single

throughput_3p7s: 0.83

us_pacific_date: 2024-11-19

win_ratio: 0.5032864799271918

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, '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-anthropic-r-8708-v1-mkmlizer
Waiting for job on chaiml-small-anthropic-r-8708-v1-mkmlizer to finish
chaiml-small-anthropic-r-8708-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║       /___/                                                         ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-r-8708-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-small-anthropic-r-8708-v1-mkmlizer: Downloaded to shared memory in 93.711s
chaiml-small-anthropic-r-8708-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjo6qw58u, device:0
chaiml-small-anthropic-r-8708-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-anthropic-r-8708-v1-mkmlizer: quantized model in 44.027s
chaiml-small-anthropic-r-8708-v1-mkmlizer: Processed model ChaiML/small_anthropic_rerun_sample200 in 137.739s
chaiml-small-anthropic-r-8708-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-anthropic-r-8708-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-anthropic-r-8708-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-anthropic-r-8708-v1
chaiml-small-anthropic-r-8708-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-anthropic-r-8708-v1/special_tokens_map.json
chaiml-small-anthropic-r-8708-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-anthropic-r-8708-v1/config.json
chaiml-small-anthropic-r-8708-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-anthropic-r-8708-v1/tokenizer_config.json
chaiml-small-anthropic-r-8708-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-anthropic-r-8708-v1/tokenizer.json
chaiml-small-anthropic-r-8708-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-anthropic-r-8708-v1/flywheel_model.1.safetensors
chaiml-small-anthropic-r-8708-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-anthropic-r-8708-v1/flywheel_model.0.safetensors
chaiml-small-anthropic-r-8708-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:19, 25.15it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:11, 42.05it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 40.36it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:11, 41.18it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 42.67it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 35.81it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:10, 43.42it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 40.94it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:13, 34.93it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:16, 27.26it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:17, 26.07it/s]
Loading 0:  12%|█▏        | 61/507 [00:01<00:15, 28.81it/s]
Loading 0:  13%|█▎        | 65/507 [00:01<00:15, 27.78it/s]
Loading 0:  14%|█▍        | 72/507 [00:02<00:11, 36.50it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:10, 40.95it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:10, 39.46it/s]
Loading 0:  17%|█▋        | 88/507 [00:02<00:10, 39.07it/s]
Loading 0:  18%|█▊        | 93/507 [00:02<00:10, 40.28it/s]
Loading 0:  19%|█▉        | 98/507 [00:02<00:12, 33.45it/s]
Loading 0:  21%|██        | 105/507 [00:02<00:10, 39.39it/s]
Loading 0:  22%|██▏       | 110/507 [00:03<00:10, 37.06it/s]
Loading 0:  22%|██▏       | 114/507 [00:03<00:14, 27.29it/s]
Loading 0:  23%|██▎       | 118/507 [00:03<00:14, 27.12it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 26.85it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:11, 34.02it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 34.15it/s]
Loading 0:  27%|██▋       | 138/507 [00:03<00:09, 37.54it/s]
Loading 0:  28%|██▊       | 143/507 [00:04<00:09, 38.06it/s]
Loading 0:  29%|██▉       | 148/507 [00:04<00:09, 39.32it/s]
Loading 0:  30%|███       | 153/507 [00:04<00:08, 41.17it/s]
Loading 0:  31%|███       | 158/507 [00:04<00:10, 34.52it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:08, 39.86it/s]
Loading 0:  33%|███▎      | 169/507 [00:04<00:10, 31.40it/s]
Loading 0:  34%|███▍      | 173/507 [00:04<00:10, 31.62it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:10, 30.12it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.57it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 34.09it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 36.96it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:09, 33.74it/s]
Loading 0:  40%|███▉      | 201/507 [00:05<00:08, 36.14it/s]
Loading 0:  40%|████      | 205/507 [00:05<00:08, 36.20it/s]
Loading 0:  41%|████▏     | 210/507 [00:05<00:07, 39.40it/s]
Loading 0:  42%|████▏     | 215/507 [00:06<00:07, 39.44it/s]
Loading 0:  43%|████▎     | 220/507 [00:06<00:08, 34.09it/s]
Loading 0:  44%|████▍     | 224/507 [00:06<00:10, 27.39it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:09, 29.12it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 35.48it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:07, 34.64it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 36.53it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 35.37it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 37.22it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 35.72it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 38.03it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 36.66it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:05, 39.07it/s]
Loading 0:  55%|█████▍    | 277/507 [00:07<00:06, 37.47it/s]
Loading 0:  56%|█████▌    | 282/507 [00:08<00:05, 40.08it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:09, 23.18it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:08, 26.08it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 26.08it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:45,  1.25it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:24,  1.42it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:37,  2.05it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:17,  2.53it/s]
Loading 0:  62%|██████▏   | 313/507 [00:23<01:00,  3.22it/s]
Loading 0:  63%|██████▎   | 318/507 [00:23<00:39,  4.84it/s]
Loading 0:  64%|██████▎   | 322/507 [00:24<00:28,  6.43it/s]
Loading 0:  64%|██████▍   | 326/507 [00:24<00:21,  8.51it/s]
Loading 0:  65%|██████▌   | 330/507 [00:24<00:16, 10.58it/s]
Loading 0:  66%|██████▌   | 335/507 [00:24<00:12, 14.24it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:10, 15.92it/s]
Loading 0:  68%|██████▊   | 344/507 [00:24<00:08, 18.46it/s]
Loading 0:  69%|██████▊   | 348/507 [00:24<00:07, 20.29it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:05, 26.44it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 27.73it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 31.51it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 30.39it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 34.32it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:03, 34.58it/s]
Loading 0:  75%|███████▌  | 381/507 [00:25<00:03, 38.20it/s]
Loading 0:  76%|███████▌  | 386/507 [00:25<00:03, 36.99it/s]
Loading 0:  77%|███████▋  | 390/507 [00:26<00:03, 29.32it/s]
Loading 0:  78%|███████▊  | 395/507 [00:26<00:04, 25.38it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 27.27it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 33.45it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 33.18it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 36.01it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 35.41it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 37.97it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 35.67it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 37.79it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 36.93it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 40.33it/s]
Loading 0:  89%|████████▊ | 449/507 [00:27<00:01, 40.20it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 39.96it/s]
Loading 0:  91%|█████████ | 459/507 [00:30<00:07,  6.22it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  8.76it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 12.72it/s]
Loading 0:  94%|█████████▍| 477/507 [00:30<00:01, 15.53it/s]
Loading 0:  95%|█████████▌| 482/507 [00:30<00:01, 18.84it/s]
Loading 0:  96%|█████████▌| 487/507 [00:30<00:00, 22.72it/s]
Loading 0:  97%|█████████▋| 492/507 [00:31<00:00, 22.85it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 29.20it/s]
Loading 0:  99%|█████████▉| 504/507 [00:31<00:00, 30.11it/s]
                                                            
Job chaiml-small-anthropic-r-8708-v1-mkmlizer completed after 166.52s with status: succeeded
Stopping job with name chaiml-small-anthropic-r-8708-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.16s
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-anthropic-r-8708-v1
Waiting for inference service chaiml-small-anthropic-r-8708-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
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
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
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-small-anthropic-r-8708-v1 ready after 221.05068111419678s
Pipeline stage MKMLDeployer completed in 222.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8130080699920654s
Received healthy response to inference request in 2.2619690895080566s
Received healthy response to inference request in 2.4363226890563965s
Received healthy response to inference request in 2.2342722415924072s
Received healthy response to inference request in 3.1340994834899902s
5 requests
0 failed requests
5th percentile: 2.2398116111755373
10th percentile: 2.245350980758667
20th percentile: 2.2564297199249266
30th percentile: 2.2968398094177247
40th percentile: 2.3665812492370604
50th percentile: 2.4363226890563965
60th percentile: 2.586996841430664
70th percentile: 2.7376709938049317
80th percentile: 2.8772263526916504
90th percentile: 3.0056629180908203
95th percentile: 3.0698812007904053
99th percentile: 3.1212558269500734
mean time: 2.575934314727783
Pipeline stage StressChecker completed in 15.25s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
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
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 OfflineFamilyFriendlyTriggerPipeline completed in 6.55s
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 3.31s
Shutdown handler de-registered
chaiml-small-anthropic-r_8708_v1 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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-small-anthropic-r-8708-v1-profiler
Waiting for inference service chaiml-small-anthropic-r-8708-v1-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 3087.53s
Shutdown handler de-registered
chaiml-small-anthropic-r_8708_v1 status is now inactive due to auto deactivation removed underperforming models