chaiml-slerpv1-ft-sft-e_58952

developer_uid: NischayDnk

submission_id: chaiml-slerpv1-ft-sft-e_58952_v1

model_name: chaiml-slerpv1-ft-sft-e_58952_v1

model_group: ChaiML/slerpv1-ft-sft-ex

status: torndown

timestamp: 2025-04-03T05:44:13+00:00

num_battles: 7840

num_wins: 4185

celo_rating: 1305.65

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/slerpv1-ft-sft-exp2-del5kdatasys

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': 0.3655801356423471, 'latency_mean': 2.735314826965332, 'latency_p50': 2.7337063550949097, 'latency_p90': 3.0132214784622193}, {'batch_size': 2, 'throughput': 0.5756709683695828, 'latency_mean': 3.4615621054172516, 'latency_p50': 3.4399352073669434, 'latency_p90': 3.8262160062789916}, {'batch_size': 3, 'throughput': 0.7265209826245552, 'latency_mean': 4.109921181201935, 'latency_p50': 4.122360467910767, 'latency_p90': 4.50041708946228}, {'batch_size': 4, 'throughput': 0.8402394859545413, 'latency_mean': 4.724598425626755, 'latency_p50': 4.7607492208480835, 'latency_p90': 5.234308648109436}, {'batch_size': 5, 'throughput': 0.9456176044011634, 'latency_mean': 5.2667912518978115, 'latency_p50': 5.274132013320923, 'latency_p90': 5.921867370605469}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-slerpv1-ft-sft-e_58952_v1

is_internal_developer: False

language_model: ChaiML/slerpv1-ft-sft-exp2-del5kdatasys

model_size: 24B

ranking_group: single

throughput_3p7s: 0.64

us_pacific_date: 2025-04-02

win_ratio: 0.5338010204081632

generation_params: {'temperature': 0.45, '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': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-slerpv1-ft-sft-e-58952-v1-mkmlizer
Waiting for job on chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer to finish
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║       /___/                                                         ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║                                                                     ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║                                                                     ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║                                                                     ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ║                                                                     ║
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: Downloaded to shared memory in 83.249s
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr900yog6, device:0
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: quantized model in 53.253s
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: Processed model ChaiML/slerpv1-ft-sft-exp2-del5kdatasys in 136.503s
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-slerpv1-ft-sft-e-58952-v1
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-slerpv1-ft-sft-e-58952-v1/config.json
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-slerpv1-ft-sft-e-58952-v1/special_tokens_map.json
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-slerpv1-ft-sft-e-58952-v1/tokenizer_config.json
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-slerpv1-ft-sft-e-58952-v1/tokenizer.json
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-slerpv1-ft-sft-e-58952-v1/flywheel_model.0.safetensors
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-slerpv1-ft-sft-e-58952-v1/flywheel_model.1.safetensors
chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.38it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 29.80it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 33.01it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.93it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.34it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.13it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 36.29it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.04it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.51it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.05it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.50it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.58it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 30.07it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.76it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.91it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.33it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.48it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.92it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.49it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 28.52it/s]
Loading 0:  25%|██▍       | 90/363 [00:03<00:10, 27.08it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:10, 25.16it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 30.24it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.48it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 23.35it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 26.03it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.88it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.30it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.14it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 28.91it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:08, 26.14it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.69it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.70it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 34.30it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 21.98it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 23.94it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 24.69it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.78it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 26.48it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.18it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 24.61it/s]
Loading 0:  50%|████▉     | 181/363 [00:06<00:06, 27.38it/s]
Loading 0:  51%|█████     | 186/363 [00:06<00:06, 29.35it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 21.07it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.03it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 22.71it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:07, 22.71it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:57,  1.10s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:27,  1.09it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:29,  1.74it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.21it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.90it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.11it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:27,  5.23it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:22,  6.30it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:15,  8.82it/s]
Loading 0:  64%|██████▎   | 231/363 [00:23<00:12, 10.26it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.38it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 16.18it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.54it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.13it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.66it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.34it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 29.89it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:04, 23.53it/s]
Loading 0:  75%|███████▍  | 271/363 [00:24<00:04, 22.22it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 23.29it/s]
Loading 0:  76%|███████▋  | 277/363 [00:24<00:03, 23.32it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 26.50it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.89it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.53it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 28.23it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 28.97it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 26.59it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.96it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.72it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:01, 25.02it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.98it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 25.44it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 30.88it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 28.67it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 29.17it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 27.92it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.67it/s]
Loading 0:  96%|█████████▌| 347/363 [00:34<00:05,  2.78it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:03,  3.50it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:01,  5.21it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.79it/s]
                                                            
Job chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer completed after 175.56s with status: succeeded
Stopping job with name chaiml-slerpv1-ft-sft-e-58952-v1-mkmlizer
Pipeline stage MKMLizer completed in 175.99s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-slerpv1-ft-sft-e-58952-v1
Waiting for inference service chaiml-slerpv1-ft-sft-e-58952-v1 to be ready
Inference service chaiml-slerpv1-ft-sft-e-58952-v1 ready after 110.55428838729858s
Pipeline stage MKMLDeployer completed in 111.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0451602935791016s
Received healthy response to inference request in 2.6712913513183594s
Received healthy response to inference request in 2.506171703338623s
Received healthy response to inference request in 2.6690282821655273s
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v3: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 2.719569444656372s
5 requests
0 failed requests
5th percentile: 2.538743019104004
10th percentile: 2.5713143348693848
20th percentile: 2.6364569664001465
30th percentile: 2.669480895996094
40th percentile: 2.6703861236572264
50th percentile: 2.6712913513183594
60th percentile: 2.6906025886535643
70th percentile: 2.7099138259887696
80th percentile: 2.784687614440918
90th percentile: 2.9149239540100096
95th percentile: 2.9800421237945556
99th percentile: 3.0321366596221924
mean time: 2.722244215011597
Pipeline stage StressChecker completed in 14.89s
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 0.65s
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 0.71s
Shutdown handler de-registered
chaiml-slerpv1-ft-sft-e_58952_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-slerpv1-ft-sft-e-58952-v1-profiler
Waiting for inference service chaiml-slerpv1-ft-sft-e-58952-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
chaiml-slerpv1-ft-sft-e_58952_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-slerpv1-ft-sft-e_58952_v1 status is now torndown due to DeploymentManager action