chaiml-exp115-dpo-sftex_19921

developer_uid: NischayDnk

submission_id: chaiml-exp115-dpo-sftex_19921_v1

model_name: chaiml-exp115-dpo-sftex_19921_v1

model_group: ChaiML/exp115-dpo-sftexp

status: torndown

timestamp: 2025-03-24T18:26:20+00:00

num_battles: 6545

num_wins: 3363

celo_rating: 1281.62

family_friendly_score: 0.5409999999999999

family_friendly_standard_error: 0.007047254784666153

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': 0.6033617541963207, 'latency_mean': 1.6573091506958009, 'latency_p50': 1.655011534690857, 'latency_p90': 1.8240237712860108}, {'batch_size': 3, 'throughput': 1.0951455490663948, 'latency_mean': 2.728340524435043, 'latency_p50': 2.721860885620117, 'latency_p90': 3.0396310091018677}, {'batch_size': 5, 'throughput': 1.308066433949698, 'latency_mean': 3.8010144197940825, 'latency_p50': 3.811562657356262, 'latency_p90': 4.3292313575744625}, {'batch_size': 6, 'throughput': 1.389427326109123, 'latency_mean': 4.287010660171509, 'latency_p50': 4.305558800697327, 'latency_p90': 4.87389109134674}, {'batch_size': 8, 'throughput': 1.4486689507982733, 'latency_mean': 5.493987287282944, 'latency_p50': 5.518050789833069, 'latency_p90': 6.173775672912598}, {'batch_size': 10, 'throughput': 1.4785751438655714, 'latency_mean': 6.712626283168793, 'latency_p50': 6.761440753936768, 'latency_p90': 7.6559899806976315}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-exp115-dpo-sftex_19921_v1

is_internal_developer: False

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

model_size: 13B

ranking_group: single

throughput_3p7s: 1.3

us_pacific_date: 2025-03-24

win_ratio: 0.5138273491214668

generation_params: {'temperature': 0.85, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.3, 'frequency_penalty': 0.3, 'stopping_words': ['\n', 'You:', '###', '</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '[INST]', 'prompt_template': "''", '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': '[/INST]{bot_name}:', '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-v1-mkmlizer
Waiting for job on chaiml-exp115-dpo-sftex-19921-v1-mkmlizer to finish
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║                                                                     ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║                                                                     ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║                                                                     ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ║                                                                     ║
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: Downloaded to shared memory in 42.928s
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7zvf2u2f, device:0
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: quantized model in 37.040s
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: Processed model ChaiML/exp115-dpo-sftexp114ft-dpov10v11filtered-10kconvo in 79.968s
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp115-dpo-sftex-19921-v1
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp115-dpo-sftex-19921-v1/config.json
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp115-dpo-sftex-19921-v1/special_tokens_map.json
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp115-dpo-sftex-19921-v1/tokenizer_config.json
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp115-dpo-sftex-19921-v1/tokenizer.json
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp115-dpo-sftex-19921-v1/flywheel_model.0.safetensors
chaiml-exp115-dpo-sftex-19921-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.01it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 45.61it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 42.31it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 42.05it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 42.40it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 33.23it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:08, 40.32it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:08, 39.45it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:08, 38.87it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:07, 40.06it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:07, 40.99it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:12, 24.79it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:09, 32.09it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 33.08it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:08, 34.74it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 37.31it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.78it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 42.23it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:06, 42.22it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 46.64it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:05, 44.13it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:05, 44.52it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 35.18it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 41.82it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 42.71it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:07, 28.89it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 30.61it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 37.60it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 37.51it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.60it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 38.80it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 31.80it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 38.42it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 37.82it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 37.73it/s]
Loading 0:  54%|█████▍    | 197/363 [00:05<00:04, 37.77it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 37.69it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:04, 35.99it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 38.70it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:04, 36.37it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 36.62it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 29.19it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 30.38it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 29.21it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.35it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 33.74it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 36.94it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 34.58it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 36.99it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 36.86it/s]
Loading 0:  73%|███████▎  | 265/363 [00:07<00:02, 40.86it/s]
Loading 0:  75%|███████▍  | 271/363 [00:07<00:02, 39.79it/s]
Loading 0:  76%|███████▌  | 276/363 [00:07<00:02, 38.65it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 44.04it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 43.89it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 43.00it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 44.40it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:23,  2.48it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:17,  3.21it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:12,  4.20it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:06,  7.01it/s]
Loading 0:  90%|████████▉ | 325/363 [00:15<00:04,  9.18it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:02, 11.23it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.76it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 20.03it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 22.62it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 28.88it/s]
Loading 0: 100%|█████████▉| 362/363 [00:16<00:00, 31.37it/s]
                                                            
Job chaiml-exp115-dpo-sftex-19921-v1-mkmlizer completed after 114.16s with status: succeeded
Stopping job with name chaiml-exp115-dpo-sftex-19921-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.60s
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-exp115-dpo-sftex-19921-v1
Waiting for inference service chaiml-exp115-dpo-sftex-19921-v1 to be ready
Inference service chaiml-exp115-dpo-sftex-19921-v1 ready after 90.3024742603302s
Pipeline stage MKMLDeployer completed in 90.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0193471908569336s
Received healthy response to inference request in 1.6702446937561035s
Received healthy response to inference request in 1.6492273807525635s
Received healthy response to inference request in 1.4844920635223389s
Received healthy response to inference request in 1.5926907062530518s
5 requests
0 failed requests
5th percentile: 1.5061317920684814
10th percentile: 1.527771520614624
20th percentile: 1.5710509777069093
30th percentile: 1.6039980411529542
40th percentile: 1.6266127109527588
50th percentile: 1.6492273807525635
60th percentile: 1.6576343059539795
70th percentile: 1.6660412311553956
80th percentile: 1.7400651931762696
90th percentile: 1.8797061920166016
95th percentile: 1.9495266914367675
99th percentile: 2.0053830909729005
mean time: 1.6832004070281983
Pipeline stage StressChecker completed in 9.64s
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 0.92s
Shutdown handler de-registered
chaiml-exp115-dpo-sftex_19921_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 2502.71s
Shutdown handler de-registered
chaiml-exp115-dpo-sftex_19921_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp115-dpo-sftex_19921_v1 status is now torndown due to DeploymentManager action