chaiml-espresso-ant-llam_7498

developer_uid: azuruce

submission_id: chaiml-espresso-ant-llam_7498_v1

model_name: chaiml-espresso-ant-llam_7498_v1

model_group: ChaiML/espresso_ant_llam

status: torndown

timestamp: 2024-12-06T02:23:10+00:00

num_battles: 7718

num_wins: 3874

celo_rating: 1265.67

family_friendly_score: 0.5856

family_friendly_standard_error: 0.006966672663474293

submission_type: basic

model_repo: ChaiML/espresso_ant_llama_241204_albert_v2_sft_4epoch_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': 0.38824435193510054, 'latency_mean': 2.5756157958507537, 'latency_p50': 2.5636943578720093, 'latency_p90': 2.844330382347107}, {'batch_size': 3, 'throughput': 0.8144652581386705, 'latency_mean': 3.6668584680557252, 'latency_p50': 3.670172333717346, 'latency_p90': 4.027891135215759}, {'batch_size': 5, 'throughput': 1.0772312383082314, 'latency_mean': 4.62490398645401, 'latency_p50': 4.637417435646057, 'latency_p90': 5.1620427608489985}, {'batch_size': 6, 'throughput': 1.1615198995816147, 'latency_mean': 5.116804438829422, 'latency_p50': 5.097259759902954, 'latency_p90': 5.80776834487915}, {'batch_size': 10, 'throughput': 1.3810264466394633, 'latency_mean': 7.177173825502396, 'latency_p50': 7.114121079444885, 'latency_p90': 8.170240354537963}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-llam_7498_v1

is_internal_developer: True

language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_4epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.83

us_pacific_date: 2024-12-05

win_ratio: 0.5019435086810055

generation_params: {'temperature': 0.8, '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-llam-7498-v1-mkmlizer
Waiting for job on chaiml-espresso-ant-llam-7498-v1-mkmlizer to finish
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-7498-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-llam-7498-v1-mkmlizer: Downloaded to shared memory in 92.187s
chaiml-espresso-ant-llam-7498-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjlweyhxk, device:0
chaiml-espresso-ant-llam-7498-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-llam-7498-v1-mkmlizer: quantized model in 48.141s
chaiml-espresso-ant-llam-7498-v1-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_4epoch_128alpha in 140.328s
chaiml-espresso-ant-llam-7498-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-llam-7498-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-llam-7498-v1
chaiml-espresso-ant-llam-7498-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-7498-v1/config.json
chaiml-espresso-ant-llam-7498-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-7498-v1/special_tokens_map.json
chaiml-espresso-ant-llam-7498-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-7498-v1/tokenizer_config.json
chaiml-espresso-ant-llam-7498-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-7498-v1/tokenizer.json
chaiml-espresso-ant-llam-7498-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-7498-v1/flywheel_model.0.safetensors
chaiml-espresso-ant-llam-7498-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 23.24it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 39.80it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 39.52it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 39.85it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 41.44it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 34.31it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:11, 41.35it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 40.73it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:12, 35.66it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:17, 26.08it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:17, 25.53it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 30.29it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:14, 29.40it/s]
Loading 0:  14%|█▍        | 72/507 [00:02<00:13, 33.07it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:11, 37.35it/s]
Loading 0:  16%|█▌        | 82/507 [00:02<00:12, 34.88it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:11, 36.55it/s]
Loading 0:  18%|█▊        | 91/507 [00:02<00:12, 33.98it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:11, 35.73it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:11, 35.19it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:10, 37.81it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:10, 36.31it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:15, 24.83it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:17, 22.68it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 25.99it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:11, 31.95it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:12, 30.52it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 33.63it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:11, 32.88it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:10, 35.30it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:10, 32.59it/s]
Loading 0:  31%|███       | 155/507 [00:04<00:10, 34.12it/s]
Loading 0:  31%|███▏      | 159/507 [00:04<00:11, 29.89it/s]
Loading 0:  32%|███▏      | 163/507 [00:04<00:10, 31.71it/s]
Loading 0:  33%|███▎      | 168/507 [00:05<00:10, 32.20it/s]
Loading 0:  34%|███▍      | 172/507 [00:05<00:16, 20.27it/s]
Loading 0:  35%|███▍      | 176/507 [00:05<00:16, 20.50it/s]
Loading 0:  36%|███▌      | 181/507 [00:05<00:12, 25.28it/s]
Loading 0:  36%|███▋      | 185/507 [00:05<00:13, 24.50it/s]
Loading 0:  37%|███▋      | 190/507 [00:06<00:10, 28.94it/s]
Loading 0:  38%|███▊      | 194/507 [00:06<00:12, 26.01it/s]
Loading 0:  39%|███▉      | 199/507 [00:06<00:10, 30.24it/s]
Loading 0:  40%|████      | 203/507 [00:06<00:11, 27.35it/s]
Loading 0:  41%|████      | 208/507 [00:06<00:09, 31.58it/s]
Loading 0:  42%|████▏     | 212/507 [00:06<00:10, 28.63it/s]
Loading 0:  43%|████▎     | 217/507 [00:06<00:08, 32.93it/s]
Loading 0:  44%|████▎     | 221/507 [00:07<00:09, 29.76it/s]
Loading 0:  44%|████▍     | 225/507 [00:07<00:13, 20.52it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:12, 22.54it/s]
Loading 0:  46%|████▋     | 235/507 [00:07<00:10, 26.61it/s]
Loading 0:  47%|████▋     | 239/507 [00:07<00:10, 24.92it/s]
Loading 0:  48%|████▊     | 244/507 [00:08<00:09, 28.66it/s]
Loading 0:  49%|████▉     | 248/507 [00:08<00:09, 26.15it/s]
Loading 0:  50%|████▉     | 253/507 [00:08<00:08, 29.93it/s]
Loading 0:  51%|█████     | 257/507 [00:08<00:09, 26.82it/s]
Loading 0:  52%|█████▏    | 262/507 [00:08<00:08, 29.62it/s]
Loading 0:  52%|█████▏    | 266/507 [00:08<00:08, 26.93it/s]
Loading 0:  53%|█████▎    | 271/507 [00:09<00:07, 30.26it/s]
Loading 0:  54%|█████▍    | 275/507 [00:09<00:08, 27.69it/s]
Loading 0:  55%|█████▌    | 280/507 [00:09<00:07, 31.15it/s]
Loading 0:  56%|█████▌    | 284/507 [00:09<00:10, 22.10it/s]
Loading 0:  57%|█████▋    | 287/507 [00:09<00:10, 21.11it/s]
Loading 0:  58%|█████▊    | 293/507 [00:10<00:08, 24.47it/s]
Loading 0:  59%|█████▉    | 299/507 [00:20<00:08, 24.47it/s]
Loading 0:  59%|█████▉    | 300/507 [00:25<03:04,  1.12it/s]
Loading 0:  60%|█████▉    | 302/507 [00:25<02:40,  1.28it/s]
Loading 0:  61%|██████    | 307/507 [00:25<01:46,  1.87it/s]
Loading 0:  61%|██████    | 310/507 [00:25<01:23,  2.35it/s]
Loading 0:  62%|██████▏   | 313/507 [00:25<01:04,  3.00it/s]
Loading 0:  62%|██████▏   | 316/507 [00:26<00:49,  3.87it/s]
Loading 0:  63%|██████▎   | 320/507 [00:26<00:35,  5.26it/s]
Loading 0:  64%|██████▍   | 325/507 [00:26<00:23,  7.80it/s]
Loading 0:  65%|██████▍   | 329/507 [00:26<00:20,  8.60it/s]
Loading 0:  66%|██████▌   | 334/507 [00:26<00:14, 11.89it/s]
Loading 0:  67%|██████▋   | 339/507 [00:27<00:11, 15.22it/s]
Loading 0:  68%|██████▊   | 343/507 [00:27<00:12, 13.66it/s]
Loading 0:  68%|██████▊   | 347/507 [00:27<00:10, 15.03it/s]
Loading 0:  69%|██████▉   | 352/507 [00:27<00:08, 19.06it/s]
Loading 0:  70%|███████   | 356/507 [00:27<00:07, 19.70it/s]
Loading 0:  71%|███████   | 361/507 [00:28<00:06, 23.77it/s]
Loading 0:  72%|███████▏  | 365/507 [00:28<00:06, 22.60it/s]
Loading 0:  73%|███████▎  | 370/507 [00:28<00:05, 26.65it/s]
Loading 0:  74%|███████▍  | 374/507 [00:28<00:05, 24.74it/s]
Loading 0:  75%|███████▍  | 379/507 [00:28<00:04, 28.85it/s]
Loading 0:  76%|███████▌  | 383/507 [00:28<00:04, 26.31it/s]
Loading 0:  77%|███████▋  | 388/507 [00:28<00:03, 29.87it/s]
Loading 0:  77%|███████▋  | 392/507 [00:29<00:04, 27.40it/s]
Loading 0:  78%|███████▊  | 395/507 [00:29<00:05, 18.84it/s]
Loading 0:  79%|███████▉  | 400/507 [00:29<00:04, 24.08it/s]
Loading 0:  80%|███████▉  | 404/507 [00:29<00:04, 25.10it/s]
Loading 0:  80%|████████  | 408/507 [00:29<00:03, 25.96it/s]
Loading 0:  81%|████████  | 411/507 [00:30<00:03, 24.10it/s]
Loading 0:  82%|████████▏ | 415/507 [00:30<00:03, 26.49it/s]
Loading 0:  83%|████████▎ | 419/507 [00:30<00:03, 25.31it/s]
Loading 0:  84%|████████▎ | 424/507 [00:30<00:02, 30.13it/s]
Loading 0:  84%|████████▍ | 428/507 [00:30<00:02, 28.13it/s]
Loading 0:  86%|████████▌ | 435/507 [00:30<00:02, 35.22it/s]
Loading 0:  87%|████████▋ | 439/507 [00:30<00:01, 35.29it/s]
Loading 0:  88%|████████▊ | 445/507 [00:30<00:01, 38.57it/s]
Loading 0:  89%|████████▊ | 449/507 [00:31<00:01, 38.50it/s]
Loading 0:  90%|████████▉ | 454/507 [00:31<00:01, 39.21it/s]
Loading 0:  90%|█████████ | 458/507 [00:33<00:08,  5.90it/s]
Loading 0:  91%|█████████ | 461/507 [00:33<00:06,  7.04it/s]
Loading 0:  92%|█████████▏| 465/507 [00:33<00:04,  8.80it/s]
Loading 0:  93%|█████████▎| 470/507 [00:33<00:03, 12.15it/s]
Loading 0:  93%|█████████▎| 474/507 [00:34<00:02, 13.93it/s]
Loading 0:  94%|█████████▍| 479/507 [00:34<00:01, 18.06it/s]
Loading 0:  95%|█████████▌| 483/507 [00:34<00:01, 19.01it/s]
Loading 0:  96%|█████████▋| 488/507 [00:34<00:00, 23.28it/s]
Loading 0:  97%|█████████▋| 492/507 [00:34<00:00, 22.66it/s]
Loading 0:  98%|█████████▊| 497/507 [00:34<00:00, 26.63it/s]
Loading 0:  99%|█████████▉| 501/507 [00:34<00:00, 25.06it/s]
Loading 0: 100%|█████████▉| 506/507 [00:35<00:00, 28.82it/s]
                                                            
Job chaiml-espresso-ant-llam-7498-v1-mkmlizer completed after 204.86s with status: succeeded
Stopping job with name chaiml-espresso-ant-llam-7498-v1-mkmlizer
Pipeline stage MKMLizer completed in 206.98s
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-llam-7498-v1
Waiting for inference service chaiml-espresso-ant-llam-7498-v1 to be ready
Inference service chaiml-espresso-ant-llam-7498-v1 ready after 184.0632562637329s
Pipeline stage MKMLDeployer completed in 187.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8001468181610107s
Received healthy response to inference request in 2.590379238128662s
Received healthy response to inference request in 2.6688289642333984s
Received healthy response to inference request in 2.671726942062378s
Received healthy response to inference request in 2.447709798812866s
5 requests
0 failed requests
5th percentile: 2.4762436866760256
10th percentile: 2.5047775745391845
20th percentile: 2.5618453502655028
30th percentile: 2.6060691833496095
40th percentile: 2.6374490737915037
50th percentile: 2.6688289642333984
60th percentile: 2.6699881553649902
70th percentile: 2.671147346496582
80th percentile: 2.6974109172821046
90th percentile: 2.7487788677215574
95th percentile: 2.774462842941284
99th percentile: 2.7950100231170656
mean time: 2.6357583522796633
Pipeline stage StressChecker completed in 15.04s
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 2.15s
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 2.02s
Shutdown handler de-registered
chaiml-espresso-ant-llam_7498_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 3067.77s
Shutdown handler de-registered
chaiml-espresso-ant-llam_7498_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-espresso-ant-llam_7498_v1 status is now torndown due to DeploymentManager action
chaiml-espresso-ant-llam_7498_v1 status is now torndown due to DeploymentManager action
chaiml-espresso-ant-llam_7498_v1 status is now torndown due to DeploymentManager action