developer_uid: NischayDnk
submission_id: chaiml-exp52-albert-sft_26828_v1
model_name: chaiml-exp52-albert-sft_26828_v1
model_group: ChaiML/exp52-albert-sft-
status: torndown
timestamp: 2025-03-07T13:57:58+00:00
num_battles: 12113
num_wins: 5647
celo_rating: 1254.79
family_friendly_score: 0.5654
family_friendly_standard_error: 0.007010318680345424
submission_type: basic
model_repo: ChaiML/exp52-albert-sft-allsamples-try1
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.37203162720133004, 'latency_mean': 2.6878784692287443, 'latency_p50': 2.6728875637054443, 'latency_p90': 2.9930060386657713}, {'batch_size': 2, 'throughput': 0.580936234491098, 'latency_mean': 3.4405991780757903, 'latency_p50': 3.41967511177063, 'latency_p90': 3.841192293167114}, {'batch_size': 3, 'throughput': 0.7289644360788388, 'latency_mean': 4.10174173951149, 'latency_p50': 4.092212677001953, 'latency_p90': 4.61940233707428}, {'batch_size': 4, 'throughput': 0.847437993656267, 'latency_mean': 4.7009992134571075, 'latency_p50': 4.756044030189514, 'latency_p90': 5.183815693855285}, {'batch_size': 5, 'throughput': 0.9359342483108535, 'latency_mean': 5.31753038764, 'latency_p50': 5.285451889038086, 'latency_p90': 5.998761940002441}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-exp52-albert-sft_26828_v1
is_internal_developer: False
language_model: ChaiML/exp52-albert-sft-allsamples-try1
model_size: 24B
ranking_group: single
throughput_3p7s: 0.65
us_pacific_date: 2025-03-07
win_ratio: 0.46619334599190954
generation_params: {'temperature': 0.5, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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-exp52-albert-sft-26828-v1-mkmlizer
Waiting for job on chaiml-exp52-albert-sft-26828-v1-mkmlizer to finish
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ _____ __ __ ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ /___/ ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ belonging to: ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ║ ║
chaiml-exp52-albert-sft-26828-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp52-albert-sft-26828-v1-mkmlizer: Downloaded to shared memory in 75.507s
chaiml-exp52-albert-sft-26828-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpx8pz2hey, device:0
chaiml-exp52-albert-sft-26828-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp52-albert-sft-26828-v1-mkmlizer: quantized model in 53.372s
chaiml-exp52-albert-sft-26828-v1-mkmlizer: Processed model ChaiML/exp52-albert-sft-allsamples-try1 in 128.879s
chaiml-exp52-albert-sft-26828-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp52-albert-sft-26828-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp52-albert-sft-26828-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp52-albert-sft-26828-v1
chaiml-exp52-albert-sft-26828-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp52-albert-sft-26828-v1/config.json
chaiml-exp52-albert-sft-26828-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp52-albert-sft-26828-v1/special_tokens_map.json
chaiml-exp52-albert-sft-26828-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp52-albert-sft-26828-v1/tokenizer_config.json
chaiml-exp52-albert-sft-26828-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp52-albert-sft-26828-v1/tokenizer.json
chaiml-exp52-albert-sft-26828-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp52-albert-sft-26828-v1/flywheel_model.1.safetensors
chaiml-exp52-albert-sft-26828-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp52-albert-sft-26828-v1/flywheel_model.0.safetensors
chaiml-exp52-albert-sft-26828-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:17, 20.49it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:09, 36.31it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:10, 34.18it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:10, 33.87it/s] Loading 0: 7%|▋ | 26/363 [00:00<00:09, 34.81it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:08, 39.36it/s] Loading 0: 10%|█ | 37/363 [00:01<00:13, 24.79it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:14, 22.84it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:10, 29.38it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:10, 28.55it/s] Loading 0: 16%|█▌ | 57/363 [00:01<00:09, 31.69it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:09, 30.21it/s] Loading 0: 18%|█▊ | 65/363 [00:02<00:09, 30.97it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:10, 27.30it/s] Loading 0: 20%|██ | 73/363 [00:02<00:12, 22.56it/s] Loading 0: 21%|██▏ | 78/363 [00:02<00:10, 27.71it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:10, 26.44it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:09, 28.46it/s] Loading 0: 25%|██▍ | 90/363 [00:03<00:09, 27.59it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:10, 25.62it/s] Loading 0: 27%|██▋ | 99/363 [00:03<00:08, 30.77it/s] Loading 0: 28%|██▊ | 103/363 [00:03<00:08, 29.47it/s] Loading 0: 29%|██▉ | 107/363 [00:03<00:10, 24.39it/s] Loading 0: 31%|███ | 112/363 [00:03<00:09, 26.88it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:09, 25.81it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 29.21it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 27.46it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 29.81it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:07, 28.91it/s] Loading 0: 38%|███▊ | 138/363 [00:04<00:07, 31.67it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:07, 30.02it/s] Loading 0: 41%|████ | 149/363 [00:05<00:06, 35.08it/s] Loading 0: 42%|████▏ | 153/363 [00:05<00:09, 22.42it/s] Loading 0: 43%|████▎ | 157/363 [00:05<00:08, 24.65it/s] Loading 0: 44%|████▍ | 160/363 [00:05<00:08, 24.50it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:07, 27.03it/s] Loading 0: 46%|████▋ | 168/363 [00:06<00:07, 24.61it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 29.84it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 28.48it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:06, 28.89it/s] Loading 0: 52%|█████▏ | 187/363 [00:06<00:06, 25.92it/s] Loading 0: 52%|█████▏ | 190/363 [00:06<00:07, 23.59it/s] Loading 0: 53%|█████▎ | 193/363 [00:06<00:07, 24.01it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:06, 23.97it/s] Loading 0: 55%|█████▌ | 200/363 [00:21<00:06, 23.97it/s] Loading 0: 55%|█████▌ | 201/363 [00:21<02:59, 1.11s/it] Loading 0: 56%|█████▌ | 203/363 [00:21<02:28, 1.08it/s] Loading 0: 57%|█████▋ | 208/363 [00:21<01:29, 1.73it/s] Loading 0: 58%|█████▊ | 211/363 [00:21<01:08, 2.22it/s] Loading 0: 59%|█████▉ | 214/363 [00:22<00:51, 2.92it/s] Loading 0: 60%|██████ | 218/363 [00:22<00:34, 4.18it/s] Loading 0: 61%|██████ | 221/363 [00:22<00:26, 5.35it/s] Loading 0: 62%|██████▏ | 224/363 [00:22<00:21, 6.44it/s] Loading 0: 63%|██████▎ | 228/363 [00:22<00:14, 9.01it/s] Loading 0: 64%|██████▎ | 231/363 [00:22<00:12, 10.44it/s] Loading 0: 65%|██████▌ | 237/363 [00:22<00:08, 15.63it/s] Loading 0: 66%|██████▋ | 241/363 [00:23<00:06, 17.72it/s] Loading 0: 68%|██████▊ | 246/363 [00:23<00:05, 21.85it/s] Loading 0: 69%|██████▉ | 250/363 [00:23<00:04, 23.14it/s] Loading 0: 70%|███████ | 255/363 [00:23<00:04, 26.72it/s] Loading 0: 71%|███████▏ | 259/363 [00:23<00:03, 26.71it/s] Loading 0: 73%|███████▎ | 266/363 [00:23<00:02, 33.07it/s] Loading 0: 74%|███████▍ | 270/363 [00:24<00:04, 21.59it/s] Loading 0: 75%|███████▌ | 274/363 [00:24<00:03, 24.24it/s] Loading 0: 77%|███████▋ | 278/363 [00:24<00:03, 25.49it/s] Loading 0: 78%|███████▊ | 282/363 [00:24<00:02, 27.35it/s] Loading 0: 79%|███████▉ | 286/363 [00:24<00:02, 26.84it/s] Loading 0: 80%|████████ | 291/363 [00:24<00:02, 30.06it/s] Loading 0: 81%|████████▏ | 295/363 [00:24<00:02, 29.03it/s] Loading 0: 82%|████████▏ | 299/363 [00:25<00:02, 29.37it/s] Loading 0: 84%|████████▎ | 304/363 [00:25<00:02, 26.94it/s] Loading 0: 85%|████████▍ | 307/363 [00:25<00:02, 24.57it/s] Loading 0: 85%|████████▌ | 310/363 [00:25<00:02, 25.05it/s] Loading 0: 86%|████████▌ | 313/363 [00:25<00:01, 25.60it/s] Loading 0: 88%|████████▊ | 318/363 [00:25<00:01, 29.10it/s] Loading 0: 88%|████████▊ | 321/363 [00:25<00:01, 25.99it/s] Loading 0: 90%|█████████ | 327/363 [00:26<00:01, 31.16it/s] Loading 0: 91%|█████████ | 331/363 [00:26<00:01, 28.07it/s] Loading 0: 92%|█████████▏| 334/363 [00:26<00:01, 28.13it/s] Loading 0: 93%|█████████▎| 337/363 [00:26<00:01, 23.56it/s] Loading 0: 94%|█████████▍| 341/363 [00:33<00:12, 1.74it/s] Loading 0: 96%|█████████▌| 347/363 [00:33<00:05, 2.85it/s] Loading 0: 96%|█████████▋| 350/363 [00:33<00:03, 3.54it/s] Loading 0: 98%|█████████▊| 355/363 [00:33<00:01, 5.19it/s] Loading 0: 99%|█████████▊| 358/363 [00:33<00:00, 6.19it/s]
Job chaiml-exp52-albert-sft-26828-v1-mkmlizer completed after 165.79s with status: succeeded
Stopping job with name chaiml-exp52-albert-sft-26828-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.34s
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-exp52-albert-sft-26828-v1
Waiting for inference service chaiml-exp52-albert-sft-26828-v1 to be ready
Inference service chaiml-exp52-albert-sft-26828-v1 ready after 100.41347241401672s
Pipeline stage MKMLDeployer completed in 100.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.399949789047241s
Received healthy response to inference request in 2.595261812210083s
Received healthy response to inference request in 2.4793190956115723s
Received healthy response to inference request in 2.6827566623687744s
Received healthy response to inference request in 2.4216768741607666s
5 requests
0 failed requests
5th percentile: 2.433205318450928
10th percentile: 2.444733762741089
20th percentile: 2.467790651321411
30th percentile: 2.5025076389312746
40th percentile: 2.548884725570679
50th percentile: 2.595261812210083
60th percentile: 2.6302597522735596
70th percentile: 2.665257692337036
80th percentile: 2.826195287704468
90th percentile: 3.1130725383758544
95th percentile: 3.2565111637115476
99th percentile: 3.3712620639801023
mean time: 2.7157928466796877
Pipeline stage StressChecker completed in 15.06s
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 0.75s
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 0.68s
Shutdown handler de-registered
chaiml-exp52-albert-sft_26828_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5436.99s
Shutdown handler de-registered
chaiml-exp52-albert-sft_26828_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp52-albert-sft_26828_v1 status is now torndown due to DeploymentManager action