developer_uid: NischayDnk
submission_id: chaiml-dolphin24b-sftex_96694_v1
model_name: chaiml-dolphin24b-sftex_96694_v1
model_group: ChaiML/dolphin24b-sftexp
status: torndown
timestamp: 2025-05-06T12:16:58+00:00
num_battles: 7554
num_wins: 3767
celo_rating: 1284.64
family_friendly_score: 0.5406
family_friendly_standard_error: 0.007047717928521259
submission_type: basic
model_repo: ChaiML/dolphin24b-sftexp1-s1-screenshot-toplex20perc
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5544750996767123, 'latency_mean': 1.803436689376831, 'latency_p50': 1.8094544410705566, 'latency_p90': 1.991629672050476}, {'batch_size': 4, 'throughput': 1.3757750020811845, 'latency_mean': 2.885362900495529, 'latency_p50': 2.8885587453842163, 'latency_p90': 3.215223479270935}, {'batch_size': 5, 'throughput': 1.5482041882081783, 'latency_mean': 3.210520466566086, 'latency_p50': 3.2462246417999268, 'latency_p90': 3.5724360942840576}, {'batch_size': 8, 'throughput': 1.8706846065579, 'latency_mean': 4.234562709331512, 'latency_p50': 4.221081256866455, 'latency_p90': 4.727005791664124}, {'batch_size': 10, 'throughput': 2.003964049531754, 'latency_mean': 4.9508579790592195, 'latency_p50': 4.987874150276184, 'latency_p90': 5.623297190666198}, {'batch_size': 12, 'throughput': 2.072071168816103, 'latency_mean': 5.7233636033535005, 'latency_p50': 5.710570454597473, 'latency_p90': 6.602036643028259}, {'batch_size': 15, 'throughput': 2.136037848112107, 'latency_mean': 6.926665732860565, 'latency_p50': 6.9173901081085205, 'latency_p90': 7.832630586624146}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-dolphin24b-sftex_96694_v1
is_internal_developer: False
language_model: ChaiML/dolphin24b-sftexp1-s1-screenshot-toplex20perc
model_size: 24B
ranking_group: single
throughput_3p7s: 1.74
us_pacific_date: 2025-05-06
win_ratio: 0.4986761980407731
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '<|im_start|>', '\n'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly{memory}\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-dolphin24b-sftex-96694-v1-mkmlizer
Waiting for job on chaiml-dolphin24b-sftex-96694-v1-mkmlizer to finish
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║       /___/                                                         ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║                                                                     ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║                                                                     ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║                                                                     ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ║                                                                     ║
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: Downloaded to shared memory in 79.461s
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_t8n06mv, device:0
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: quantized model in 53.141s
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: Processed model ChaiML/dolphin24b-sftexp1-s1-screenshot-toplex20perc in 132.603s
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-dolphin24b-sftex-96694-v1
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-dolphin24b-sftex-96694-v1/config.json
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-dolphin24b-sftex-96694-v1/special_tokens_map.json
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-dolphin24b-sftex-96694-v1/tokenizer_config.json
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-dolphin24b-sftex-96694-v1/flywheel_model.1.safetensors
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-dolphin24b-sftex-96694-v1/flywheel_model.0.safetensors
chaiml-dolphin24b-sftex-96694-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.54it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 36.28it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 34.30it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.90it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 31.06it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 36.30it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 23.23it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 25.91it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:11, 27.00it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.70it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.85it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 29.70it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.05it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.53it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.98it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.50it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.29it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:10, 25.64it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.41it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 27.90it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 22.49it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.48it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.19it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 24.09it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 26.72it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.63it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.99it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.28it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.02it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.61it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 30.79it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.88it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 35.37it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:08, 24.44it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:08, 24.12it/s]
Loading 0:  44%|████▍     | 159/363 [00:05<00:08, 23.00it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.37it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 25.07it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.83it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.60it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.39it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 25.90it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:07, 24.23it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 25.14it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 25.50it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 25.50it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:56,  1.09s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:26,  1.09it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:28,  1.76it/s]
Loading 0:  58%|█████▊    | 211/363 [00:21<01:07,  2.24it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:50,  2.94it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.18it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.31it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.33it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.37it/s]
Loading 0:  64%|██████▍   | 232/363 [00:22<00:11, 11.19it/s]
Loading 0:  65%|██████▌   | 237/363 [00:22<00:08, 15.03it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.80it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 20.93it/s]
Loading 0:  69%|██████▊   | 249/363 [00:23<00:05, 20.42it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.42it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:04, 25.56it/s]
Loading 0:  73%|███████▎  | 264/363 [00:23<00:03, 30.42it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:03, 24.01it/s]
Loading 0:  75%|███████▍  | 271/363 [00:24<00:04, 21.66it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 22.96it/s]
Loading 0:  76%|███████▋  | 277/363 [00:24<00:03, 23.28it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 26.44it/s]
Loading 0:  79%|███████▊  | 285/363 [00:24<00:03, 24.11it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 28.88it/s]
Loading 0:  81%|████████  | 294/363 [00:25<00:02, 25.94it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 28.21it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 24.97it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.39it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.37it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:02, 24.54it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.65it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.90it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 29.58it/s]
Loading 0:  91%|█████████ | 330/363 [00:26<00:01, 26.37it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 28.35it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 27.05it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:12,  1.70it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:05,  2.83it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:03,  3.55it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:01,  5.24it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.76it/s]
                                                            

Job chaiml-dolphin24b-sftex-96694-v1-mkmlizer completed after 166.42s with status: succeeded
Stopping job with name chaiml-dolphin24b-sftex-96694-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.90s
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-dolphin24b-sftex-96694-v1
Waiting for inference service chaiml-dolphin24b-sftex-96694-v1 to be ready
Inference service chaiml-dolphin24b-sftex-96694-v1 ready after 150.57946395874023s
Pipeline stage MKMLDeployer completed in 151.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.604158639907837s
Received healthy response to inference request in 1.9065196514129639s
Received healthy response to inference request in 2.300572156906128s
Received healthy response to inference request in 1.9322731494903564s
Received healthy response to inference request in 2.231635093688965s
5 requests
0 failed requests
5th percentile: 1.9116703510284423
10th percentile: 1.916821050643921
20th percentile: 1.927122449874878
30th percentile: 1.9921455383300781
40th percentile: 2.1118903160095215
50th percentile: 2.231635093688965
60th percentile: 2.25920991897583
70th percentile: 2.2867847442626954
80th percentile: 2.36128945350647
90th percentile: 2.4827240467071534
95th percentile: 2.543441343307495
99th percentile: 2.5920151805877687
mean time: 2.19503173828125
Pipeline stage StressChecker completed in 12.22s
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 0.84s
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 0.69s
Shutdown handler de-registered
chaiml-dolphin24b-sftex_96694_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 3989.98s
Shutdown handler de-registered
chaiml-dolphin24b-sftex_96694_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-dolphin24b-sftex_96694_v1 status is now torndown due to DeploymentManager action