chaiml-supermega-sft-ex_48753

developer_uid: NischayDnk

submission_id: chaiml-supermega-sft-ex_48753_v3

model_name: chaiml-supermega-sft-ex_48753_v3

model_group: ChaiML/supermega-sft-exp

status: torndown

timestamp: 2025-03-12T23:31:08+00:00

num_battles: 11685

num_wins: 5869

celo_rating: 1283.97

family_friendly_score: 0.5678000000000001

family_friendly_standard_error: 0.007005757061160485

submission_type: basic

model_repo: ChaiML/supermega-sft-exp69-24B-2Msamp-epoch2ckpt

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': 0.3750201056314565, 'latency_mean': 2.6664630830287934, 'latency_p50': 2.655809760093689, 'latency_p90': 2.9431078910827635}, {'batch_size': 2, 'throughput': 0.5795847617761563, 'latency_mean': 3.4438107550144195, 'latency_p50': 3.4571781158447266, 'latency_p90': 3.7939626693725588}, {'batch_size': 3, 'throughput': 0.72370329120266, 'latency_mean': 4.133854222297669, 'latency_p50': 4.1511582136154175, 'latency_p90': 4.539430546760559}, {'batch_size': 4, 'throughput': 0.8466320422892292, 'latency_mean': 4.705829277038574, 'latency_p50': 4.683709383010864, 'latency_p90': 5.275624346733093}, {'batch_size': 5, 'throughput': 0.9351109249724733, 'latency_mean': 5.3231452322006225, 'latency_p50': 5.367632985115051, 'latency_p90': 5.849129629135132}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-supermega-sft-ex_48753_v3

is_internal_developer: False

language_model: ChaiML/supermega-sft-exp69-24B-2Msamp-epoch2ckpt

model_size: 24B

ranking_group: single

throughput_3p7s: 0.64

us_pacific_date: 2025-03-12

win_ratio: 0.5022678647839109

generation_params: {'temperature': 0.4, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 50, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, '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-supermega-sft-ex-48753-v3-mkmlizer
Waiting for job on chaiml-supermega-sft-ex-48753-v3-mkmlizer to finish
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║       /___/                                                         ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║                                                                     ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║                                                                     ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║                                                                     ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ║                                                                     ║
chaiml-supermega-sft-ex-48753-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-supermega-sft-ex-48753-v3-mkmlizer: Downloaded to shared memory in 61.370s
chaiml-supermega-sft-ex-48753-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvjo80er0, device:0
chaiml-supermega-sft-ex-48753-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-supermega-sft-ex-48753-v3-mkmlizer: quantized model in 53.271s
chaiml-supermega-sft-ex-48753-v3-mkmlizer: Processed model ChaiML/supermega-sft-exp69-24B-2Msamp-epoch2ckpt in 114.641s
chaiml-supermega-sft-ex-48753-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-supermega-sft-ex-48753-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-supermega-sft-ex-48753-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-supermega-sft-ex-48753-v3
chaiml-supermega-sft-ex-48753-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-supermega-sft-ex-48753-v3/config.json
chaiml-supermega-sft-ex-48753-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-supermega-sft-ex-48753-v3/special_tokens_map.json
chaiml-supermega-sft-ex-48753-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-supermega-sft-ex-48753-v3/tokenizer_config.json
chaiml-supermega-sft-ex-48753-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-supermega-sft-ex-48753-v3/tokenizer.json
chaiml-supermega-sft-ex-48753-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-supermega-sft-ex-48753-v3/flywheel_model.1.safetensors
chaiml-supermega-sft-ex-48753-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-supermega-sft-ex-48753-v3/flywheel_model.0.safetensors
chaiml-supermega-sft-ex-48753-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.65it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.67it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 33.25it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 29.57it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.36it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.00it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 34.88it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.49it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.97it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.74it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.63it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.60it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.94it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.87it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.59it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 24.66it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.13it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.42it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 25.66it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.48it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.45it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.77it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.95it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.85it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 23.67it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 26.39it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.72it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.16it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.92it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.59it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.02it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.79it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.49it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 34.30it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 21.68it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 24.21it/s]
Loading 0:  44%|████▍     | 161/363 [00:06<00:08, 25.03it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.80it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 26.35it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.54it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.27it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.40it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 26.09it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.64it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 24.18it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.32it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.32it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:58,  1.10s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:27,  1.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:28,  1.74it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<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,  5.34it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.38it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.37it/s]
Loading 0:  64%|██████▍   | 232/363 [00:22<00:11, 11.14it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.17it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 16.07it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.30it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 21.44it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 24.81it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:04, 24.54it/s]
Loading 0:  73%|███████▎  | 265/363 [00:23<00:03, 31.10it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 22.32it/s]
Loading 0:  75%|███████▍  | 272/363 [00:24<00:03, 22.82it/s]
Loading 0:  76%|███████▌  | 275/363 [00:24<00:04, 19.63it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 26.71it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:03, 25.33it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 27.79it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 26.91it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.72it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.61it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.49it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 23.95it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.01it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.42it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.79it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 29.68it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 28.14it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 28.53it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 26.64it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.67it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:05,  2.79it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:03,  3.50it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:01,  5.19it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.71it/s]
                                                            
Job chaiml-supermega-sft-ex-48753-v3-mkmlizer completed after 144.58s with status: succeeded
Stopping job with name chaiml-supermega-sft-ex-48753-v3-mkmlizer
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Pipeline stage MKMLizer completed in 145.22s
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-supermega-sft-ex-48753-v3
Waiting for inference service chaiml-supermega-sft-ex-48753-v3 to be ready
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-supermega-sft-ex-48753-v3 ready after 90.34206461906433s
Pipeline stage MKMLDeployer completed in 90.88s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.261718988418579s
Received healthy response to inference request in 2.4678430557250977s
Received healthy response to inference request in 2.60444974899292s
Received healthy response to inference request in 2.1315813064575195s
Received healthy response to inference request in 2.0893735885620117s
5 requests
0 failed requests
5th percentile: 2.0978151321411134
10th percentile: 2.106256675720215
20th percentile: 2.123139762878418
30th percentile: 2.1988336563110353
40th percentile: 2.3333383560180665
50th percentile: 2.4678430557250977
60th percentile: 2.5224857330322266
70th percentile: 2.5771284103393555
80th percentile: 2.735903596878052
90th percentile: 2.9988112926483153
95th percentile: 3.130265140533447
99th percentile: 3.2354282188415526
mean time: 2.5109933376312257
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 0.68s
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 0.73s
Shutdown handler de-registered
chaiml-supermega-sft-ex_48753_v3 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-supermega-sft-ex-48753-v3-profiler
Waiting for inference service chaiml-supermega-sft-ex-48753-v3-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4706.67s
Shutdown handler de-registered
chaiml-supermega-sft-ex_48753_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-supermega-sft-ex_48753_v3 status is now torndown due to DeploymentManager action