chaiml-exp115-dpo-sftex_19921

developer_uid: NischayDnk

submission_id: chaiml-exp115-dpo-sftex_19921_v3

model_name: chaiml-exp115-dpo-sftex_19921_v3

model_group: ChaiML/exp115-dpo-sftexp

status: torndown

timestamp: 2025-03-24T18:38:35+00:00

num_battles: 5776

num_wins: 2072

celo_rating: 1171.74

family_friendly_score: 0.65

family_friendly_standard_error: 0.00674536878161602

submission_type: basic

model_repo: ChaiML/exp115-dpo-sftexp114ft-dpov10v11filtered-10kconvo

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6012551036008122, 'latency_mean': 1.6631156384944916, 'latency_p50': 1.670822024345398, 'latency_p90': 1.8300634622573853}, {'batch_size': 3, 'throughput': 1.097767607305186, 'latency_mean': 2.7301908433437347, 'latency_p50': 2.7203482389450073, 'latency_p90': 2.9962180852890015}, {'batch_size': 5, 'throughput': 1.3155263680837417, 'latency_mean': 3.7894200122356416, 'latency_p50': 3.820440411567688, 'latency_p90': 4.20385365486145}, {'batch_size': 6, 'throughput': 1.3885522640420238, 'latency_mean': 4.291223828792572, 'latency_p50': 4.283865928649902, 'latency_p90': 4.849909400939941}, {'batch_size': 8, 'throughput': 1.4344294914222486, 'latency_mean': 5.526554681062699, 'latency_p50': 5.553533911705017, 'latency_p90': 6.184022831916809}, {'batch_size': 10, 'throughput': 1.4783591659224182, 'latency_mean': 6.703869259357452, 'latency_p50': 6.696245908737183, 'latency_p90': 7.609873914718627}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-exp115-dpo-sftex_19921_v3

is_internal_developer: False

language_model: ChaiML/exp115-dpo-sftexp114ft-dpov10v11filtered-10kconvo

model_size: 13B

ranking_group: single

throughput_3p7s: 1.31

us_pacific_date: 2025-03-24

win_ratio: 0.3587257617728532

generation_params: {'temperature': 0.85, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 80, 'presence_penalty': 0.3, 'frequency_penalty': 0.3, 'stopping_words': ['\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-exp115-dpo-sftex-19921-v3-mkmlizer
Waiting for job on chaiml-exp115-dpo-sftex-19921-v3-mkmlizer to finish
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║       /___/                                                         ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║                                                                     ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║                                                                     ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║                                                                     ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ║                                                                     ║
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: Downloaded to shared memory in 45.186s
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpu3eq0jpt, device:0
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: quantized model in 35.543s
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: Processed model ChaiML/exp115-dpo-sftexp114ft-dpov10v11filtered-10kconvo in 80.729s
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp115-dpo-sftex-19921-v3
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp115-dpo-sftex-19921-v3/config.json
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp115-dpo-sftex-19921-v3/special_tokens_map.json
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp115-dpo-sftex-19921-v3/tokenizer.json
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp115-dpo-sftex-19921-v3/flywheel_model.0.safetensors
chaiml-exp115-dpo-sftex-19921-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.01it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 50.94it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 47.98it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 49.54it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.58it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 49.99it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 51.09it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 53.33it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.47it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.47it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.88it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.98it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 42.05it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 37.96it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 46.62it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 45.28it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.23it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 51.98it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 45.46it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:06, 40.16it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 39.90it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:06, 38.19it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 38.30it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:05, 37.92it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:07, 28.46it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 28.48it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 27.08it/s]
Loading 0:  42%|████▏     | 154/363 [00:03<00:07, 28.30it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 27.57it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 36.80it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 39.58it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 42.23it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 42.44it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 40.97it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:03, 45.07it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:03, 45.92it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 46.55it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:03, 44.55it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:03, 41.38it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 43.18it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 34.65it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 34.81it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 33.57it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 40.30it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:02, 40.76it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 40.78it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 44.70it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 45.69it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 46.79it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 44.86it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:01, 43.59it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 48.56it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 46.17it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 44.88it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 45.78it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:23,  2.52it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:16,  3.26it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.24it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  7.05it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.52it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 12.02it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.82it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.57it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 24.08it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 31.03it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 34.39it/s]
                                                            
Job chaiml-exp115-dpo-sftex-19921-v3-mkmlizer completed after 104.07s with status: succeeded
Stopping job with name chaiml-exp115-dpo-sftex-19921-v3-mkmlizer
Pipeline stage MKMLizer completed in 104.54s
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-exp115-dpo-sftex-19921-v3
Waiting for inference service chaiml-exp115-dpo-sftex-19921-v3 to be ready
Inference service chaiml-exp115-dpo-sftex-19921-v3 ready after 90.35866689682007s
Pipeline stage MKMLDeployer completed in 90.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.387554407119751s
Received healthy response to inference request in 0.6772167682647705s
Received healthy response to inference request in 0.6190929412841797s
Received healthy response to inference request in 0.5835411548614502s
Received healthy response to inference request in 0.37335681915283203s
5 requests
0 failed requests
5th percentile: 0.41539368629455564
10th percentile: 0.4574305534362793
20th percentile: 0.5415042877197266
30th percentile: 0.5906515121459961
40th percentile: 0.6048722267150879
50th percentile: 0.6190929412841797
60th percentile: 0.642342472076416
70th percentile: 0.6655920028686524
80th percentile: 0.8192842960357667
90th percentile: 1.1034193515777588
95th percentile: 1.2454868793487548
99th percentile: 1.3591409015655518
mean time: 0.7281524181365967
Pipeline stage StressChecker completed in 5.09s
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 0.71s
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-exp115-dpo-sftex_19921_v3 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 2356.87s
Shutdown handler de-registered
chaiml-exp115-dpo-sftex_19921_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp115-dpo-sftex_19921_v3 status is now torndown due to DeploymentManager action