chaiml-dolphin24b-sftex_23877

developer_uid: NischayDnk

submission_id: chaiml-dolphin24b-sftex_23877_v1

model_name: chaiml-dolphin24b-sftex_23877_v1

model_group: ChaiML/dolphin24b-sftexp

status: torndown

timestamp: 2025-05-06T15:58:49+00:00

num_battles: 11483

num_wins: 5945

celo_rating: 1295.58

family_friendly_score: 0.5466

family_friendly_standard_error: 0.007040290334922275

submission_type: basic

model_repo: ChaiML/dolphin24b-sftexp1-s1-screenshot-toplex20perc-1

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': 0.5352096046031387, 'latency_mean': 1.8683727478981018, 'latency_p50': 1.8536179065704346, 'latency_p90': 2.092972016334534}, {'batch_size': 3, 'throughput': 1.075954175842077, 'latency_mean': 2.7781672191619875, 'latency_p50': 2.7994080781936646, 'latency_p90': 3.0884065866470336}, {'batch_size': 5, 'throughput': 1.3985350726698793, 'latency_mean': 3.548722050189972, 'latency_p50': 3.564368963241577, 'latency_p90': 3.9123363971710203}, {'batch_size': 6, 'throughput': 1.5116439596225697, 'latency_mean': 3.9487161350250246, 'latency_p50': 3.945960521697998, 'latency_p90': 4.400334167480469}, {'batch_size': 8, 'throughput': 1.6510855482493163, 'latency_mean': 4.816615912914276, 'latency_p50': 4.7935813665390015, 'latency_p90': 5.400836610794068}, {'batch_size': 10, 'throughput': 1.7592157385716387, 'latency_mean': 5.63692996263504, 'latency_p50': 5.618930816650391, 'latency_p90': 6.392997241020202}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-dolphin24b-sftex_23877_v1

is_internal_developer: False

language_model: ChaiML/dolphin24b-sftexp1-s1-screenshot-toplex20perc-1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.45

us_pacific_date: 2025-05-06

win_ratio: 0.5177218496908473

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_start|>', '\n', '<|im_end|>'], 'max_input_tokens': 1024, '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-23877-v1-mkmlizer
Waiting for job on chaiml-dolphin24b-sftex-23877-v1-mkmlizer to finish
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║       /___/                                                         ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║                                                                     ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║                                                                     ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║                                                                     ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ║                                                                     ║
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: Downloaded to shared memory in 80.589s
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdqmusdrg, device:0
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: quantized model in 53.546s
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: Processed model ChaiML/dolphin24b-sftexp1-s1-screenshot-toplex20perc-1 in 134.135s
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-dolphin24b-sftex-23877-v1
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-dolphin24b-sftex-23877-v1/config.json
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-dolphin24b-sftex-23877-v1/special_tokens_map.json
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-dolphin24b-sftex-23877-v1/tokenizer_config.json
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-dolphin24b-sftex-23877-v1/tokenizer.json
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-dolphin24b-sftex-23877-v1/flywheel_model.1.safetensors
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-dolphin24b-sftex-23877-v1/flywheel_model.0.safetensors
chaiml-dolphin24b-sftex-23877-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.21it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 36.92it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 33.00it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 34.10it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.54it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:08, 37.45it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.00it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.70it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.27it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.46it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.75it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.23it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.78it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.27it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.08it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.71it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.15it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 25.95it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.18it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.90it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.23it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.13it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 25.01it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.87it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.80it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.87it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.69it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.35it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.27it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:08, 25.73it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.92it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.13it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.60it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 23.52it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 21.97it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 23.04it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.49it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.66it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 24.07it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.07it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.54it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 27.39it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.26it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.80it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.90it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.49it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.49it/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<00:50,  2.93it/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,  6.35it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.36it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.14it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.97it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.79it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.20it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.03it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.26it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:04, 25.21it/s]
Loading 0:  73%|███████▎  | 265/363 [00:24<00:03, 31.77it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 21.82it/s]
Loading 0:  75%|███████▍  | 272/363 [00:24<00:04, 22.74it/s]
Loading 0:  76%|███████▌  | 275/363 [00:24<00:04, 19.39it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 26.08it/s]
Loading 0:  79%|███████▉  | 286/363 [00:25<00:02, 25.68it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 27.55it/s]
Loading 0:  81%|████████  | 294/363 [00:25<00:02, 24.71it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 26.88it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 23.96it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 22.51it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.55it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 23.95it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 26.87it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.18it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 29.02it/s]
Loading 0:  91%|█████████ | 330/363 [00:26<00:01, 25.94it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:01, 27.88it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 26.68it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:12,  1.69it/s]
Loading 0:  96%|█████████▌| 347/363 [00:34<00:05,  2.82it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:03,  3.52it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:01,  5.21it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.77it/s]
                                                            
Job chaiml-dolphin24b-sftex-23877-v1-mkmlizer completed after 165.94s with status: succeeded
Stopping job with name chaiml-dolphin24b-sftex-23877-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.43s
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-dolphin24b-sftex-23877-v1
Waiting for inference service chaiml-dolphin24b-sftex-23877-v1 to be ready
Inference service chaiml-dolphin24b-sftex-23877-v1 ready after 150.69746279716492s
Pipeline stage MKMLDeployer completed in 151.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6333398818969727s
Received healthy response to inference request in 1.8534209728240967s
Received healthy response to inference request in 2.178009510040283s
Received healthy response to inference request in 1.9409635066986084s
Received healthy response to inference request in 2.0843584537506104s
5 requests
0 failed requests
5th percentile: 1.870929479598999
10th percentile: 1.8884379863739014
20th percentile: 1.923454999923706
30th percentile: 1.9696424961090089
40th percentile: 2.0270004749298094
50th percentile: 2.0843584537506104
60th percentile: 2.1218188762664796
70th percentile: 2.159279298782349
80th percentile: 2.2690755844116213
90th percentile: 2.451207733154297
95th percentile: 2.5422738075256346
99th percentile: 2.615126667022705
mean time: 2.1380184650421143
Pipeline stage StressChecker completed in 12.01s
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 0.81s
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 0.79s
Shutdown handler de-registered
chaiml-dolphin24b-sftex_23877_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 2878.41s
Shutdown handler de-registered
chaiml-dolphin24b-sftex_23877_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-dolphin24b-sftex_23877_v1 status is now torndown due to DeploymentManager action