chaiml-exp311-stage2-dp_72252

developer_uid: NischayDnk

submission_id: chaiml-exp311-stage2-dp_72252_v1

model_name: chaiml-exp311-stage2-dp_72252_v1

model_group: ChaiML/exp311-stage2-dpo

status: torndown

timestamp: 2025-04-13T17:43:26+00:00

num_battles: 8319

num_wins: 4804

celo_rating: 1341.48

family_friendly_score: 0.3456

family_friendly_standard_error: 0.006725483477044606

submission_type: basic

model_repo: ChaiML/exp311-stage2-dpo-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': 0.3652514908840739, 'latency_mean': 2.7377752161026, 'latency_p50': 2.7561182975769043, 'latency_p90': 3.0257061958312987}, {'batch_size': 2, 'throughput': 0.5711686305276241, 'latency_mean': 3.4961987316608427, 'latency_p50': 3.5037763118743896, 'latency_p90': 3.855721950531006}, {'batch_size': 3, 'throughput': 0.7261602329708449, 'latency_mean': 4.1195768392086025, 'latency_p50': 4.141304612159729, 'latency_p90': 4.564377498626709}, {'batch_size': 4, 'throughput': 0.8368323635397273, 'latency_mean': 4.755900588035583, 'latency_p50': 4.762230396270752, 'latency_p90': 5.278394174575806}, {'batch_size': 5, 'throughput': 0.9282476740455481, 'latency_mean': 5.354661854505539, 'latency_p50': 5.364939332008362, 'latency_p90': 5.962962126731872}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp311-stage2-dp_72252_v1

is_internal_developer: False

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

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-04-13

win_ratio: 0.5774732539968747

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': ['\n', '<|im_start|>', '<|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-exp311-stage2-dp-72252-v1-mkmlizer
Waiting for job on chaiml-exp311-stage2-dp-72252-v1-mkmlizer to finish
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║                                                                     ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║                                                                     ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║                                                                     ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ║                                                                     ║
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: Downloaded to shared memory in 81.365s
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpijuv3ze1, device:0
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: quantized model in 53.043s
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: Processed model ChaiML/exp311-stage2-dpo-v1-ft-simpo1350-datav1full in 134.409s
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp311-stage2-dp-72252-v1
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp311-stage2-dp-72252-v1/config.json
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp311-stage2-dp-72252-v1/special_tokens_map.json
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp311-stage2-dp-72252-v1/tokenizer_config.json
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp311-stage2-dp-72252-v1/tokenizer.json
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp311-stage2-dp-72252-v1/flywheel_model.0.safetensors
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp311-stage2-dp-72252-v1/flywheel_model.1.safetensors
chaiml-exp311-stage2-dp-72252-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.81it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 29.51it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.86it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 28.23it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.47it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.46it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:09, 34.33it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 24.13it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:14, 22.32it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.39it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 24.25it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.47it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.99it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 30.16it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.96it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.63it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.59it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.06it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.55it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.26it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 28.43it/s]
Loading 0:  25%|██▍       | 90/363 [00:03<00:09, 27.46it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:10, 24.78it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.92it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.92it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 23.42it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 26.22it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.37it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.38it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.38it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.99it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 27.70it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.11it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 29.16it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 34.79it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 22.63it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 25.24it/s]
Loading 0:  44%|████▍     | 161/363 [00:05<00:07, 26.18it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.93it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 26.45it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.20it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.18it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.73it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 26.03it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.49it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 24.26it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.35it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.35it/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,  1.75it/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,  4.20it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.38it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.52it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:13,  9.57it/s]
Loading 0:  64%|██████▍   | 232/363 [00:22<00:11, 11.36it/s]
Loading 0:  65%|██████▌   | 237/363 [00:22<00:08, 15.17it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 16.10it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.83it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.59it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 26.14it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:03, 26.14it/s]
Loading 0:  73%|███████▎  | 266/363 [00:23<00:03, 32.13it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 21.25it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 24.01it/s]
Loading 0:  77%|███████▋  | 278/363 [00:24<00:03, 25.36it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 27.00it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:02, 26.78it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 29.86it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 27.77it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 28.49it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 26.25it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.42it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.18it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:02, 23.86it/s]
Loading 0:  88%|████████▊ | 318/363 [00:25<00:01, 27.26it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.64it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 30.09it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 28.52it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 28.69it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 27.37it/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 [00:33<00:03,  3.48it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:01,  5.14it/s]
Loading 0:  99%|█████████▊| 358/363 [00:34<00:00,  6.21it/s]
                                                            
Job chaiml-exp311-stage2-dp-72252-v1-mkmlizer completed after 168.09s with status: succeeded
Stopping job with name chaiml-exp311-stage2-dp-72252-v1-mkmlizer
Pipeline stage MKMLizer completed in 168.59s
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-exp311-stage2-dp-72252-v1
Waiting for inference service chaiml-exp311-stage2-dp-72252-v1 to be ready
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)
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)
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)
Inference service chaiml-exp311-stage2-dp-72252-v1 ready after 120.41889071464539s
Pipeline stage MKMLDeployer completed in 120.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1193392276763916s
Received healthy response to inference request in 2.5595791339874268s
Received healthy response to inference request in 2.4837558269500732s
Received healthy response to inference request in 2.553713321685791s
Received healthy response to inference request in 2.52983021736145s
5 requests
0 failed requests
5th percentile: 2.4929707050323486
10th percentile: 2.502185583114624
20th percentile: 2.520615339279175
30th percentile: 2.5346068382263183
40th percentile: 2.544160079956055
50th percentile: 2.553713321685791
60th percentile: 2.556059646606445
70th percentile: 2.5584059715270997
80th percentile: 2.67153115272522
90th percentile: 2.8954351902008058
95th percentile: 3.0073872089385985
99th percentile: 3.096948823928833
mean time: 2.6492435455322267
Pipeline stage StressChecker completed in 14.68s
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 0.66s
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 0.70s
Shutdown handler de-registered
chaiml-exp311-stage2-dp_72252_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
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 5008.70s
Shutdown handler de-registered
chaiml-exp311-stage2-dp_72252_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp311-stage2-dp_72252_v1 status is now torndown due to DeploymentManager action