alexxi19-ft-v1-nemo-base-dpo

developer_uid: leosheng

submission_id: alexxi19-ft-v1-nemo-base-dpo_v3

model_name: alexxi19-ft-v1-nemo-base-dpo_v3

model_group: alexxi19/ft-v1-nemo-base

status: torndown

timestamp: 2025-02-21T07:06:56+00:00

num_battles: 6179

num_wins: 2883

celo_rating: 1247.76

family_friendly_score: 0.5638000000000001

family_friendly_standard_error: 0.00701326685646568

submission_type: basic

model_repo: alexxi19/ft-v1-nemo-base-dpo

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6076695131502847, 'latency_mean': 1.6455667650699615, 'latency_p50': 1.647328495979309, 'latency_p90': 1.819836711883545}, {'batch_size': 3, 'throughput': 1.1047773931516485, 'latency_mean': 2.711143661737442, 'latency_p50': 2.7227803468704224, 'latency_p90': 3.003805923461914}, {'batch_size': 5, 'throughput': 1.3438819415627001, 'latency_mean': 3.7114133274555208, 'latency_p50': 3.704441785812378, 'latency_p90': 4.162012362480163}, {'batch_size': 6, 'throughput': 1.4060552472615673, 'latency_mean': 4.235711036920548, 'latency_p50': 4.253856539726257, 'latency_p90': 4.76971971988678}, {'batch_size': 8, 'throughput': 1.4509196949940915, 'latency_mean': 5.483848943710327, 'latency_p50': 5.543389201164246, 'latency_p90': 6.068483257293701}, {'batch_size': 10, 'throughput': 1.5044334024342134, 'latency_mean': 6.601165690422058, 'latency_p50': 6.621047377586365, 'latency_p90': 7.456532716751099}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-v1-nemo-base-dpo_v3

is_internal_developer: False

language_model: alexxi19/ft-v1-nemo-base-dpo

model_size: 13B

ranking_group: single

throughput_3p7s: 1.35

us_pacific_date: 2025-02-20

win_ratio: 0.4665803528078977

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|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}:', '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 alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer to finish
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: quantized model in 37.660s
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-dpo in 89.165s
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v3
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v3/config.json
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v3/special_tokens_map.json
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v3/tokenizer_config.json
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v3/tokenizer.json
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v3/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.17it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 46.07it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 45.56it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 35.11it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 44.07it/s]
Loading 0:  10%|▉         | 36/363 [00:00<00:07, 44.43it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:09, 35.03it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:07, 42.70it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:07, 42.12it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:06, 43.86it/s]
Loading 0:  17%|█▋        | 63/363 [00:01<00:10, 29.27it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:09, 30.99it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 33.75it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 34.24it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 36.13it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:07, 36.01it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 34.84it/s]
Loading 0:  26%|██▌       | 93/363 [00:02<00:07, 33.89it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:07, 37.59it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:07, 35.99it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:07, 35.98it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:06, 41.16it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:06, 39.56it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:05, 40.66it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:07, 33.24it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 39.43it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 38.96it/s]
Loading 0:  40%|███▉      | 144/363 [00:04<00:08, 24.92it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 26.93it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 34.07it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.18it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.01it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:05, 38.26it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 32.42it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 38.95it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 38.50it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 39.01it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:04, 40.25it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 33.38it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 39.72it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 39.57it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 40.77it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 25.42it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 27.67it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 33.94it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 34.30it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 35.28it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 34.67it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:02, 36.72it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 34.99it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 37.40it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 35.63it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 37.23it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 35.60it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 38.22it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:02, 36.45it/s]
Loading 0:  80%|████████  | 291/363 [00:08<00:01, 37.21it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:01, 35.23it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 34.61it/s]
Loading 0:  84%|████████▎ | 304/363 [00:15<00:27,  2.11it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:21,  2.65it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:13,  3.90it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:06,  6.34it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:05,  7.97it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03, 11.27it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:01, 14.52it/s]
Loading 0:  93%|█████████▎| 339/363 [00:16<00:01, 16.55it/s]
Loading 0:  95%|█████████▌| 346/363 [00:16<00:00, 23.05it/s]
Loading 0:  97%|█████████▋| 351/363 [00:16<00:00, 26.22it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 29.52it/s]
Loading 0:  99%|█████████▉| 361/363 [00:16<00:00, 32.83it/s]
                                                            
Job alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer completed after 114.42s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-base-dpo-v3-mkmlizer
Pipeline stage MKMLizer completed in 114.97s
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 alexxi19-ft-v1-nemo-base-dpo-v3
Waiting for inference service alexxi19-ft-v1-nemo-base-dpo-v3 to be ready
Inference service alexxi19-ft-v1-nemo-base-dpo-v3 ready after 210.79310393333435s
Pipeline stage MKMLDeployer completed in 211.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3660874366760254s
Received healthy response to inference request in 1.574185848236084s
Received healthy response to inference request in 1.9160716533660889s
Received healthy response to inference request in 1.7494473457336426s
Received healthy response to inference request in 1.5138061046600342s
5 requests
0 failed requests
5th percentile: 1.5258820533752442
10th percentile: 1.5379580020904542
20th percentile: 1.562109899520874
30th percentile: 1.6092381477355957
40th percentile: 1.6793427467346191
50th percentile: 1.7494473457336426
60th percentile: 1.8160970687866211
70th percentile: 1.8827467918395995
80th percentile: 2.006074810028076
90th percentile: 2.186081123352051
95th percentile: 2.276084280014038
99th percentile: 2.348086805343628
mean time: 1.823919677734375
Pipeline stage StressChecker completed in 10.35s
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 0.65s
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 0.65s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-base-dpo_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4133.83s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-base-dpo_v3 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-base-dpo_v3 status is now torndown due to DeploymentManager action