chaiml-exp73-dpo-ftexp1_25679

developer_uid: NischayDnk

submission_id: chaiml-exp73-dpo-ftexp1_25679_v2

model_name: chaiml-exp73-dpo-ftexp1_25679_v2

model_group: ChaiML/exp73-dpo-ftexp13

status: torndown

timestamp: 2025-03-13T11:38:39+00:00

num_battles: 11639

num_wins: 6111

celo_rating: 1291.68

family_friendly_score: 0.5589999999999999

family_friendly_standard_error: 0.007021666468866205

submission_type: basic

model_repo: ChaiML/exp73-dpo-ftexp13sft-24B-ssdelfiltered5k-5e

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': 0.3696499298687907, 'latency_mean': 2.7051648223400115, 'latency_p50': 2.706387758255005, 'latency_p90': 2.9731590509414674}, {'batch_size': 2, 'throughput': 0.5770949619606959, 'latency_mean': 3.456041021347046, 'latency_p50': 3.4529212713241577, 'latency_p90': 3.8078831911087034}, {'batch_size': 3, 'throughput': 0.7269475717221107, 'latency_mean': 4.114138197898865, 'latency_p50': 4.106786847114563, 'latency_p90': 4.499377202987671}, {'batch_size': 4, 'throughput': 0.8476086912871237, 'latency_mean': 4.702107065916062, 'latency_p50': 4.687903046607971, 'latency_p90': 5.182635855674743}, {'batch_size': 5, 'throughput': 0.936414540639068, 'latency_mean': 5.3034120976924894, 'latency_p50': 5.296671509742737, 'latency_p90': 5.86721875667572}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp73-dpo-ftexp1_25679_v2

is_internal_developer: False

language_model: ChaiML/exp73-dpo-ftexp13sft-24B-ssdelfiltered5k-5e

model_size: 24B

ranking_group: single

throughput_3p7s: 0.64

us_pacific_date: 2025-03-13

win_ratio: 0.5250451069679526

generation_params: {'temperature': 0.45, 'top_p': 0.925, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['###', '</s>', 'You:', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '[INST]<|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}:[/INST]', '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-exp73-dpo-ftexp1-25679-v2-mkmlizer
Waiting for job on chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer to finish
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║       /___/                                                         ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║                                                                     ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║                                                                     ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║                                                                     ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ║                                                                     ║
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: Downloaded to shared memory in 59.703s
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjr98z2ar, device:0
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: quantized model in 52.669s
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: Processed model ChaiML/exp73-dpo-ftexp13sft-24B-ssdelfiltered5k-5e in 112.373s
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp73-dpo-ftexp1-25679-v2
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp73-dpo-ftexp1-25679-v2/config.json
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp73-dpo-ftexp1-25679-v2/tokenizer.json
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp73-dpo-ftexp1-25679-v2/flywheel_model.1.safetensors
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp73-dpo-ftexp1-25679-v2/flywheel_model.0.safetensors
chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.85it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 37.44it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 35.24it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 36.48it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 32.52it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 39.39it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.60it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.71it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 28.82it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.37it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 30.55it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 29.27it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 29.90it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 26.84it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.93it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.32it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 28.28it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:11, 24.48it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 26.93it/s]
Loading 0:  26%|██▌       | 94/363 [00:03<00:09, 27.01it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 29.32it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.87it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 23.36it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:09, 26.60it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 24.21it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.64it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.30it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.62it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 28.81it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 30.59it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.83it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 34.26it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 22.20it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 24.76it/s]
Loading 0:  44%|████▍     | 161/363 [00:05<00:07, 26.00it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:07, 27.79it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 26.27it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.33it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.83it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.09it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 25.54it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:07, 23.43it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 24.11it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.66it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.66it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:58,  1.10s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:27,  1.09it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:28,  1.75it/s]
Loading 0:  58%|█████▊    | 211/363 [00:21<01:08,  2.23it/s]
Loading 0:  59%|█████▉    | 214/363 [00:21<00:50,  2.93it/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,  6.47it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.49it/s]
Loading 0:  64%|██████▍   | 232/363 [00:22<00:11, 11.29it/s]
Loading 0:  65%|██████▌   | 237/363 [00:22<00:08, 15.46it/s]
Loading 0:  66%|██████▌   | 240/363 [00:22<00:07, 16.23it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 22.04it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:04, 22.90it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 26.27it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:03, 26.20it/s]
Loading 0:  73%|███████▎  | 266/363 [00:23<00:03, 32.28it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 22.09it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 24.58it/s]
Loading 0:  77%|███████▋  | 278/363 [00:24<00:03, 26.14it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:02, 28.14it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:02, 27.53it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 30.03it/s]
Loading 0:  81%|████████▏ | 295/363 [00:24<00:02, 28.39it/s]
Loading 0:  82%|████████▏ | 299/363 [00:24<00:02, 28.66it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 26.01it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.13it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.04it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:02, 23.88it/s]
Loading 0:  88%|████████▊ | 318/363 [00:25<00:01, 27.62it/s]
Loading 0:  88%|████████▊ | 321/363 [00:25<00:01, 25.54it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 31.07it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 28.76it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 29.31it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 28.43it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.68it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:05,  2.81it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:03,  3.53it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:01,  5.25it/s]
Loading 0:  99%|█████████▉| 359/363 [00:33<00:00,  6.84it/s]
                                                            
Job chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer completed after 145.08s with status: succeeded
Stopping job with name chaiml-exp73-dpo-ftexp1-25679-v2-mkmlizer
Pipeline stage MKMLizer completed in 145.80s
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-exp73-dpo-ftexp1-25679-v2
Waiting for inference service chaiml-exp73-dpo-ftexp1-25679-v2 to be ready
Inference service chaiml-exp73-dpo-ftexp1-25679-v2 ready after 100.68750739097595s
Pipeline stage MKMLDeployer completed in 101.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1674740314483643s
Received healthy response to inference request in 2.698409080505371s
Received healthy response to inference request in 2.4791791439056396s
Received healthy response to inference request in 2.437098979949951s
Received healthy response to inference request in 2.37361216545105s
5 requests
0 failed requests
5th percentile: 2.38630952835083
10th percentile: 2.39900689125061
20th percentile: 2.424401617050171
30th percentile: 2.445515012741089
40th percentile: 2.462347078323364
50th percentile: 2.4791791439056396
60th percentile: 2.5668711185455324
70th percentile: 2.6545630931854247
80th percentile: 2.79222207069397
90th percentile: 2.979848051071167
95th percentile: 3.0736610412597654
99th percentile: 3.1487114334106443
mean time: 2.631154680252075
Pipeline stage StressChecker completed in 14.53s
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 0.73s
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 0.76s
Shutdown handler de-registered
chaiml-exp73-dpo-ftexp1_25679_v2 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-exp73-dpo-ftexp1-25679-v2-profiler
Waiting for inference service chaiml-exp73-dpo-ftexp1-25679-v2-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 5369.47s
Shutdown handler de-registered
chaiml-exp73-dpo-ftexp1_25679_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp73-dpo-ftexp1_25679_v2 status is now torndown due to DeploymentManager action