chaiml-exp311-stage2-si_96959

developer_uid: NischayDnk

submission_id: chaiml-exp311-stage2-si_96959_v3

model_name: chaiml-exp311-stage2-si_96959_v3

model_group: ChaiML/exp311-stage2-sim

status: torndown

timestamp: 2025-04-13T23:00:02+00:00

num_battles: 6756

num_wins: 4062

celo_rating: 1352.81

family_friendly_score: 0.41479999999999995

family_friendly_standard_error: 0.006967653263474008

submission_type: basic

model_repo: ChaiML/exp311-stage2-simpo-v1-ft-simpo1350-datav1full

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': 0.3696264129842487, 'latency_mean': 2.7053712928295135, 'latency_p50': 2.690916657447815, 'latency_p90': 3.011137580871582}, {'batch_size': 2, 'throughput': 0.5782587285259672, 'latency_mean': 3.458596885204315, 'latency_p50': 3.4652233123779297, 'latency_p90': 3.792607235908508}, {'batch_size': 3, 'throughput': 0.7185205792728183, 'latency_mean': 4.159755144119263, 'latency_p50': 4.162691950798035, 'latency_p90': 4.561241149902344}, {'batch_size': 4, 'throughput': 0.8365094297122295, 'latency_mean': 4.758419152498245, 'latency_p50': 4.765772581100464, 'latency_p90': 5.2619757652282715}, {'batch_size': 5, 'throughput': 0.9290368433072135, 'latency_mean': 5.347638667821884, 'latency_p50': 5.350553870201111, 'latency_p90': 6.01430070400238}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp311-stage2-si_96959_v3

is_internal_developer: False

language_model: ChaiML/exp311-stage2-simpo-v1-ft-simpo1350-datav1full

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-04-13

win_ratio: 0.6012433392539964

generation_params: {'temperature': 0.4, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['<|im_end|>', '\n', '<|im_start|>'], '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-exp311-stage2-si-96959-v3-mkmlizer
Waiting for job on chaiml-exp311-stage2-si-96959-v3-mkmlizer to finish
chaiml-exp311-stage2-si-96959-v3-mkmlizer: Downloaded to shared memory in 77.803s
chaiml-exp311-stage2-si-96959-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2fxaykp1, device:0
chaiml-exp311-stage2-si-96959-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission jellywibble-felix-black_21853_v1: HTTPConnectionPool(host='jellywibble-felix-black-21853-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission jellywibble-roan-knight-_7016_v3: HTTPConnectionPool(host='jellywibble-roan-knight-7016-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-exp311-stage2-si-96959-v3-mkmlizer: quantized model in 53.602s
chaiml-exp311-stage2-si-96959-v3-mkmlizer: Processed model ChaiML/exp311-stage2-simpo-v1-ft-simpo1350-datav1full in 131.405s
chaiml-exp311-stage2-si-96959-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp311-stage2-si-96959-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp311-stage2-si-96959-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp311-stage2-si-96959-v3
chaiml-exp311-stage2-si-96959-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp311-stage2-si-96959-v3/tokenizer_config.json
chaiml-exp311-stage2-si-96959-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp311-stage2-si-96959-v3/tokenizer.json
chaiml-exp311-stage2-si-96959-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp311-stage2-si-96959-v3/flywheel_model.1.safetensors
chaiml-exp311-stage2-si-96959-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp311-stage2-si-96959-v3/flywheel_model.0.safetensors
chaiml-exp311-stage2-si-96959-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.32it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 29.94it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 32.62it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.89it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.25it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.41it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.88it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.19it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.85it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.58it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.04it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.15it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 30.61it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 29.19it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.03it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.51it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.52it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.67it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 25.06it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.01it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.29it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.65it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:10, 26.50it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 22.45it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.27it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.23it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 22.95it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.49it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.93it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.89it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 28.67it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 31.07it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.52it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 33.98it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 21.48it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 23.84it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.87it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.26it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 27.04it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.73it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.60it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 29.18it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:06, 26.02it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.56it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 24.41it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 25.35it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 25.35it/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,  1.74it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.22it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:50,  2.92it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.19it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.36it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.43it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.44it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.19it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.98it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.78it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 20.68it/s]
Loading 0:  69%|██████▊   | 249/363 [00:23<00:05, 20.04it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.32it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 24.58it/s]
Loading 0:  72%|███████▏  | 263/363 [00:24<00:03, 27.27it/s]
Loading 0:  74%|███████▎  | 267/363 [00:24<00:04, 22.88it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 19.81it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 22.75it/s]
Loading 0:  76%|███████▋  | 277/363 [00:24<00:03, 23.39it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 26.68it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.87it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.33it/s]
Loading 0:  81%|████████  | 294/363 [00:25<00:02, 25.08it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.95it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 24.86it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.09it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.91it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.44it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 28.01it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.77it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 29.48it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 28.18it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 28.79it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 26.98it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.66it/s]
Loading 0:  96%|█████████▌| 347/363 [00:34<00:05,  2.78it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:03,  3.49it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:01,  5.17it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.68it/s]
                                                            
Job chaiml-exp311-stage2-si-96959-v3-mkmlizer completed after 166.08s with status: succeeded
Stopping job with name chaiml-exp311-stage2-si-96959-v3-mkmlizer
Pipeline stage MKMLizer completed in 166.51s
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-exp311-stage2-si-96959-v3
Waiting for inference service chaiml-exp311-stage2-si-96959-v3 to be ready
Inference service chaiml-exp311-stage2-si-96959-v3 ready after 120.50036406517029s
Pipeline stage MKMLDeployer completed in 120.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1139156818389893s
Received healthy response to inference request in 2.488074541091919s
Received healthy response to inference request in 2.632801055908203s
Received healthy response to inference request in 2.52250337600708s
Received healthy response to inference request in 2.454815626144409s
5 requests
0 failed requests
5th percentile: 2.461467409133911
10th percentile: 2.468119192123413
20th percentile: 2.481422758102417
30th percentile: 2.494960308074951
40th percentile: 2.5087318420410156
50th percentile: 2.52250337600708
60th percentile: 2.5666224479675295
70th percentile: 2.6107415199279784
80th percentile: 2.7290239810943606
90th percentile: 2.9214698314666747
95th percentile: 3.0176927566528318
99th percentile: 3.0946710968017577
mean time: 2.64242205619812
Pipeline stage StressChecker completed in 14.46s
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 0.63s
Shutdown handler de-registered
chaiml-exp311-stage2-si_96959_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp311-stage2-si-96959-v3-profiler
Waiting for inference service chaiml-exp311-stage2-si-96959-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2894.89s
Shutdown handler de-registered
chaiml-exp311-stage2-si_96959_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp311-stage2-si_96959_v3 status is now torndown due to DeploymentManager action