chaiml-1-5-k-payload-lex_3681

developer_uid: azuruce

submission_id: chaiml-1-5-k-payload-lex_3681_v1

model_name: ant_rank0_2epoch

model_group: ChaiML/1_5_k_payload_lex

status: inactive

timestamp: 2024-11-22T00:00:56+00:00

num_battles: 10719

num_wins: 5592

celo_rating: 1267.46

family_friendly_score: 0.5833999999999999

family_friendly_standard_error: 0.006972007458401059

submission_type: basic

model_repo: ChaiML/1_5_k_payload_lexical_filtered_for_albert-run2-rank0-fixed

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.38711158777372395, 'latency_mean': 2.5831669962406156, 'latency_p50': 2.596867084503174, 'latency_p90': 2.8618361949920654}, {'batch_size': 3, 'throughput': 0.8276164895341559, 'latency_mean': 3.609714308977127, 'latency_p50': 3.611242890357971, 'latency_p90': 3.943149137496948}, {'batch_size': 5, 'throughput': 1.102131916903043, 'latency_mean': 4.505882232189179, 'latency_p50': 4.4924304485321045, 'latency_p90': 5.103135275840759}, {'batch_size': 6, 'throughput': 1.1779707226430922, 'latency_mean': 5.058691966533661, 'latency_p50': 5.051146030426025, 'latency_p90': 5.643474435806274}, {'batch_size': 10, 'throughput': 1.4107672937969162, 'latency_mean': 7.044109973907471, 'latency_p50': 6.962370872497559, 'latency_p90': 7.949604535102845}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: ant_rank0_2epoch

is_internal_developer: True

language_model: ChaiML/1_5_k_payload_lexical_filtered_for_albert-run2-rank0-fixed

model_size: 22B

ranking_group: single

throughput_3p7s: 0.87

us_pacific_date: 2024-11-21

win_ratio: 0.5216904561992723

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-1-5-k-payload-lex-3681-v1-mkmlizer
Waiting for job on chaiml-1-5-k-payload-lex-3681-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
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-1-5-k-payload-lex-3681-v1-mkmlizer: Downloaded to shared memory in 117.310s
chaiml-1-5-k-payload-lex-3681-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp78yy7a8x, device:0
chaiml-1-5-k-payload-lex-3681-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1-5-k-payload-lex-3681-v1-mkmlizer: quantized model in 45.000s
chaiml-1-5-k-payload-lex-3681-v1-mkmlizer: Processed model ChaiML/1_5_k_payload_lexical_filtered_for_albert-run2-rank0-fixed in 162.310s
chaiml-1-5-k-payload-lex-3681-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1-5-k-payload-lex-3681-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-3681-v1/special_tokens_map.json
chaiml-1-5-k-payload-lex-3681-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-3681-v1/config.json
chaiml-1-5-k-payload-lex-3681-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-3681-v1/tokenizer_config.json
chaiml-1-5-k-payload-lex-3681-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-3681-v1/tokenizer.json
chaiml-1-5-k-payload-lex-3681-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-3681-v1/flywheel_model.1.safetensors
chaiml-1-5-k-payload-lex-3681-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-3681-v1/flywheel_model.0.safetensors
chaiml-1-5-k-payload-lex-3681-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 23.67it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:14, 33.20it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:17, 28.91it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:14, 34.09it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:16, 29.85it/s]
Loading 0:   6%|▌         | 28/507 [00:00<00:13, 34.56it/s]
Loading 0:   6%|▋         | 32/507 [00:01<00:15, 30.76it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:13, 35.13it/s]
Loading 0:   8%|▊         | 41/507 [00:01<00:14, 31.45it/s]
Loading 0:   9%|▉         | 46/507 [00:01<00:12, 35.54it/s]
Loading 0:  10%|▉         | 50/507 [00:01<00:14, 31.99it/s]
Loading 0:  11%|█         | 54/507 [00:01<00:20, 21.63it/s]
Loading 0:  11%|█         | 57/507 [00:02<00:20, 21.72it/s]
Loading 0:  12%|█▏        | 61/507 [00:02<00:17, 25.08it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:18, 24.55it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:14, 29.28it/s]
Loading 0:  15%|█▍        | 74/507 [00:02<00:13, 31.47it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:13, 31.24it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:12, 34.10it/s]
Loading 0:  18%|█▊        | 89/507 [00:03<00:13, 30.17it/s]
Loading 0:  19%|█▊        | 94/507 [00:03<00:12, 33.81it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:13, 30.08it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:12, 33.59it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:13, 30.30it/s]
Loading 0:  22%|██▏       | 112/507 [00:03<00:11, 33.96it/s]
Loading 0:  23%|██▎       | 116/507 [00:04<00:18, 21.19it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:15, 24.50it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:13, 28.68it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:13, 27.21it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:11, 31.14it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:12, 28.99it/s]
Loading 0:  29%|██▊       | 145/507 [00:04<00:11, 32.84it/s]
Loading 0:  29%|██▉       | 149/507 [00:05<00:11, 30.52it/s]
Loading 0:  30%|███       | 154/507 [00:05<00:10, 34.34it/s]
Loading 0:  31%|███       | 158/507 [00:05<00:11, 31.71it/s]
Loading 0:  32%|███▏      | 164/507 [00:05<00:09, 36.36it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 27.57it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 28.37it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 27.94it/s]
Loading 0:  36%|███▌      | 183/507 [00:06<00:09, 33.69it/s]
Loading 0:  37%|███▋      | 187/507 [00:06<00:09, 33.75it/s]
Loading 0:  38%|███▊      | 192/507 [00:06<00:08, 36.65it/s]
Loading 0:  39%|███▊      | 196/507 [00:06<00:08, 35.80it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 37.86it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 35.51it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 37.46it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:08, 35.85it/s]
Loading 0:  43%|████▎     | 218/507 [00:07<00:08, 35.56it/s]
Loading 0:  44%|████▍     | 222/507 [00:07<00:08, 34.59it/s]
Loading 0:  45%|████▍     | 226/507 [00:07<00:11, 25.13it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:10, 25.54it/s]
Loading 0:  46%|████▋     | 235/507 [00:07<00:08, 30.62it/s]
Loading 0:  47%|████▋     | 239/507 [00:07<00:09, 28.07it/s]
Loading 0:  48%|████▊     | 244/507 [00:07<00:08, 31.99it/s]
Loading 0:  49%|████▉     | 248/507 [00:08<00:08, 29.25it/s]
Loading 0:  50%|████▉     | 253/507 [00:08<00:07, 33.22it/s]
Loading 0:  51%|█████     | 257/507 [00:08<00:08, 30.16it/s]
Loading 0:  52%|█████▏    | 262/507 [00:08<00:07, 34.42it/s]
Loading 0:  52%|█████▏    | 266/507 [00:08<00:07, 30.88it/s]
Loading 0:  53%|█████▎    | 271/507 [00:08<00:06, 34.67it/s]
Loading 0:  54%|█████▍    | 275/507 [00:08<00:07, 31.27it/s]
Loading 0:  55%|█████▌    | 280/507 [00:09<00:06, 34.82it/s]
Loading 0:  56%|█████▌    | 284/507 [00:09<00:09, 24.52it/s]
Loading 0:  57%|█████▋    | 288/507 [00:09<00:08, 24.49it/s]
Loading 0:  58%|█████▊    | 293/507 [00:09<00:08, 25.74it/s]
Loading 0:  59%|█████▉    | 298/507 [00:09<00:06, 29.99it/s]
Loading 0:  59%|█████▉    | 299/507 [00:20<00:06, 29.99it/s]
Loading 0:  59%|█████▉    | 300/507 [00:24<04:00,  1.16s/it]
Loading 0:  60%|█████▉    | 302/507 [00:24<03:18,  1.03it/s]
Loading 0:  61%|██████    | 307/507 [00:24<02:00,  1.66it/s]
Loading 0:  61%|██████▏   | 311/507 [00:24<01:24,  2.32it/s]
Loading 0:  62%|██████▏   | 316/507 [00:25<00:54,  3.51it/s]
Loading 0:  63%|██████▎   | 320/507 [00:25<00:39,  4.69it/s]
Loading 0:  64%|██████▍   | 327/507 [00:25<00:23,  7.62it/s]
Loading 0:  65%|██████▌   | 331/507 [00:25<00:18,  9.40it/s]
Loading 0:  66%|██████▌   | 335/507 [00:25<00:14, 11.58it/s]
Loading 0:  67%|██████▋   | 340/507 [00:25<00:12, 13.05it/s]
Loading 0:  68%|██████▊   | 343/507 [00:26<00:11, 14.32it/s]
Loading 0:  68%|██████▊   | 347/507 [00:26<00:09, 16.19it/s]
Loading 0:  69%|██████▉   | 352/507 [00:26<00:07, 20.96it/s]
Loading 0:  70%|███████   | 356/507 [00:26<00:06, 22.02it/s]
Loading 0:  71%|███████   | 361/507 [00:26<00:05, 26.88it/s]
Loading 0:  72%|███████▏  | 365/507 [00:26<00:05, 26.45it/s]
Loading 0:  73%|███████▎  | 370/507 [00:26<00:04, 30.60it/s]
Loading 0:  74%|███████▍  | 374/507 [00:27<00:04, 28.88it/s]
Loading 0:  75%|███████▌  | 381/507 [00:27<00:03, 36.32it/s]
Loading 0:  76%|███████▌  | 386/507 [00:27<00:03, 35.90it/s]
Loading 0:  77%|███████▋  | 390/507 [00:27<00:03, 29.38it/s]
Loading 0:  78%|███████▊  | 394/507 [00:27<00:03, 31.33it/s]
Loading 0:  79%|███████▊  | 398/507 [00:27<00:04, 26.69it/s]
Loading 0:  79%|███████▉  | 401/507 [00:27<00:04, 24.59it/s]
Loading 0:  80%|████████  | 408/507 [00:28<00:03, 32.08it/s]
Loading 0:  81%|████████▏ | 412/507 [00:28<00:02, 31.94it/s]
Loading 0:  82%|████████▏ | 417/507 [00:28<00:02, 34.39it/s]
Loading 0:  83%|████████▎ | 421/507 [00:28<00:02, 33.30it/s]
Loading 0:  84%|████████▍ | 426/507 [00:28<00:02, 35.57it/s]
Loading 0:  85%|████████▍ | 430/507 [00:28<00:02, 33.88it/s]
Loading 0:  86%|████████▌ | 435/507 [00:28<00:02, 35.55it/s]
Loading 0:  87%|████████▋ | 439/507 [00:28<00:01, 34.46it/s]
Loading 0:  88%|████████▊ | 444/507 [00:29<00:01, 37.00it/s]
Loading 0:  88%|████████▊ | 448/507 [00:29<00:01, 35.47it/s]
Loading 0:  89%|████████▉ | 453/507 [00:29<00:01, 39.10it/s]
Loading 0:  90%|█████████ | 457/507 [00:31<00:08,  5.72it/s]
Loading 0:  91%|█████████ | 460/507 [00:31<00:06,  6.84it/s]
Loading 0:  92%|█████████▏| 465/507 [00:31<00:04,  9.36it/s]
Loading 0:  93%|█████████▎| 472/507 [00:32<00:02, 14.14it/s]
Loading 0:  94%|█████████▍| 476/507 [00:32<00:01, 16.37it/s]
Loading 0:  95%|█████████▍| 481/507 [00:32<00:01, 20.13it/s]
Loading 0:  96%|█████████▌| 485/507 [00:32<00:01, 21.98it/s]
Loading 0:  96%|█████████▋| 489/507 [00:32<00:00, 24.95it/s]
Loading 0:  97%|█████████▋| 493/507 [00:32<00:00, 24.72it/s]
Loading 0:  98%|█████████▊| 498/507 [00:32<00:00, 29.72it/s]
Loading 0:  99%|█████████▉| 502/507 [00:32<00:00, 28.40it/s]
Loading 0: 100%|█████████▉| 506/507 [00:33<00:00, 30.54it/s]
                                                            
Job chaiml-1-5-k-payload-lex-3681-v1-mkmlizer completed after 195.9s with status: succeeded
Stopping job with name chaiml-1-5-k-payload-lex-3681-v1-mkmlizer
Pipeline stage MKMLizer completed in 196.54s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1-5-k-payload-lex-3681-v1
Waiting for inference service chaiml-1-5-k-payload-lex-3681-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
Inference service chaiml-1-5-k-payload-lex-3681-v1 ready after 462.4506492614746s
Pipeline stage MKMLDeployer completed in 463.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8228423595428467s
Received healthy response to inference request in 2.5474157333374023s
Received healthy response to inference request in 2.223453998565674s
Received healthy response to inference request in 2.4088780879974365s
Received healthy response to inference request in 2.227924108505249s
5 requests
0 failed requests
5th percentile: 2.224348020553589
10th percentile: 2.225242042541504
20th percentile: 2.227030086517334
30th percentile: 2.2641149044036863
40th percentile: 2.3364964962005614
50th percentile: 2.4088780879974365
60th percentile: 2.4642931461334228
70th percentile: 2.519708204269409
80th percentile: 2.602501058578491
90th percentile: 2.712671709060669
95th percentile: 2.767757034301758
99th percentile: 2.811825294494629
mean time: 2.4461028575897217
Pipeline stage StressChecker completed in 13.78s
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 2.63s
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-1-5-k-payload-lex_3681_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 3173.58s
Shutdown handler de-registered
chaiml-1-5-k-payload-lex_3681_v1 status is now inactive due to auto deactivation removed underperforming models