alexxi19-ft-v1-nemo-base-dpo

developer_uid: leosheng

submission_id: alexxi19-ft-v1-nemo-base-dpo_v2

model_name: alexxi19-ft-v1-nemo-base-dpo_v2

model_group: alexxi19/ft-v1-nemo-base

status: torndown

timestamp: 2025-02-20T07:35:08+00:00

num_battles: 6243

num_wins: 3097

celo_rating: 1239.13

family_friendly_score: 0.5554

family_friendly_standard_error: 0.007027529295563271

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

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.60494053844957, 'latency_mean': 1.6529767465591432, 'latency_p50': 1.6566486358642578, 'latency_p90': 1.8127989530563355}, {'batch_size': 3, 'throughput': 1.1092970440951422, 'latency_mean': 2.6983793282508852, 'latency_p50': 2.6752851009368896, 'latency_p90': 3.021862602233887}, {'batch_size': 5, 'throughput': 1.3193041078357755, 'latency_mean': 3.763740336894989, 'latency_p50': 3.764170527458191, 'latency_p90': 4.168387341499328}, {'batch_size': 6, 'throughput': 1.3895752124839547, 'latency_mean': 4.2854938888549805, 'latency_p50': 4.29497754573822, 'latency_p90': 4.78347225189209}, {'batch_size': 8, 'throughput': 1.4581153615672018, 'latency_mean': 5.447249938249588, 'latency_p50': 5.414585590362549, 'latency_p90': 6.160426282882691}, {'batch_size': 10, 'throughput': 1.4938504896355385, 'latency_mean': 6.649787899255752, 'latency_p50': 6.682695627212524, 'latency_p90': 7.471080040931701}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexxi19-ft-v1-nemo-base-dpo_v2

is_internal_developer: False

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

model_size: 13B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-02-19

win_ratio: 0.4960756046772385

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-v2-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer to finish
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: Downloaded to shared memory in 47.354s
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmps8xvdzzx, device:0
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: quantized model in 39.306s
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-dpo in 86.660s
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v2
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v2/config.json
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v2/special_tokens_map.json
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v2/tokenizer_config.json
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v2/tokenizer.json
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v2/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.74it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 42.43it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 40.17it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 39.07it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:08, 38.04it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:08, 37.20it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:09, 34.63it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:08, 36.61it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:09, 34.60it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:08, 36.47it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:08, 34.73it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:08, 34.39it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:12, 24.22it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.73it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 30.66it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 30.34it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 33.09it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 32.51it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 34.83it/s]
Loading 0:  26%|██▌       | 93/363 [00:02<00:08, 33.32it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:07, 35.46it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:07, 33.84it/s]
Loading 0:  29%|██▉       | 106/363 [00:03<00:07, 33.40it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:06, 37.50it/s]
Loading 0:  32%|███▏      | 115/363 [00:03<00:07, 35.23it/s]
Loading 0:  33%|███▎      | 119/363 [00:03<00:07, 32.01it/s]
Loading 0:  34%|███▍      | 123/363 [00:03<00:07, 32.59it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:07, 30.01it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 34.30it/s]
Loading 0:  37%|███▋      | 136/363 [00:04<00:07, 31.19it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:06, 35.06it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:09, 22.38it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:09, 23.01it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.93it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 27.36it/s]
Loading 0:  45%|████▍     | 163/363 [00:05<00:06, 32.09it/s]
Loading 0:  46%|████▌     | 167/363 [00:05<00:06, 29.95it/s]
Loading 0:  47%|████▋     | 172/363 [00:05<00:05, 34.35it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:05, 31.73it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 35.84it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 32.42it/s]
Loading 0:  52%|█████▏    | 190/363 [00:05<00:04, 35.92it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:05, 31.75it/s]
Loading 0:  55%|█████▍    | 199/363 [00:06<00:04, 35.74it/s]
Loading 0:  56%|█████▌    | 203/363 [00:06<00:04, 32.68it/s]
Loading 0:  57%|█████▋    | 208/363 [00:06<00:04, 36.75it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 33.30it/s]
Loading 0:  60%|█████▉    | 217/363 [00:06<00:03, 37.34it/s]
Loading 0:  61%|██████    | 222/363 [00:06<00:03, 37.85it/s]
Loading 0:  62%|██████▏   | 226/363 [00:07<00:05, 24.25it/s]
Loading 0:  63%|██████▎   | 230/363 [00:07<00:05, 24.70it/s]
Loading 0:  65%|██████▍   | 235/363 [00:07<00:04, 29.57it/s]
Loading 0:  66%|██████▌   | 239/363 [00:07<00:04, 28.48it/s]
Loading 0:  67%|██████▋   | 244/363 [00:07<00:03, 32.72it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 30.51it/s]
Loading 0:  70%|██████▉   | 253/363 [00:07<00:03, 34.65it/s]
Loading 0:  71%|███████   | 257/363 [00:08<00:03, 31.72it/s]
Loading 0:  72%|███████▏  | 262/363 [00:08<00:02, 35.82it/s]
Loading 0:  73%|███████▎  | 266/363 [00:08<00:02, 33.00it/s]
Loading 0:  75%|███████▍  | 271/363 [00:08<00:02, 36.75it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 32.59it/s]
Loading 0:  77%|███████▋  | 280/363 [00:08<00:02, 36.68it/s]
Loading 0:  78%|███████▊  | 284/363 [00:08<00:02, 33.21it/s]
Loading 0:  80%|███████▉  | 289/363 [00:08<00:02, 36.40it/s]
Loading 0:  81%|████████  | 293/363 [00:09<00:02, 32.08it/s]
Loading 0:  82%|████████▏ | 298/363 [00:09<00:01, 35.82it/s]
Loading 0:  83%|████████▎ | 303/363 [00:09<00:01, 36.57it/s]
Loading 0:  85%|████████▍ | 307/363 [00:16<00:27,  2.05it/s]
Loading 0:  86%|████████▌ | 312/363 [00:16<00:17,  2.94it/s]
Loading 0:  87%|████████▋ | 317/363 [00:16<00:10,  4.18it/s]
Loading 0:  88%|████████▊ | 321/363 [00:16<00:07,  5.38it/s]
Loading 0:  90%|█████████ | 327/363 [00:16<00:04,  8.03it/s]
Loading 0:  91%|█████████▏| 332/363 [00:16<00:02, 10.40it/s]
Loading 0:  93%|█████████▎| 337/363 [00:17<00:01, 13.49it/s]
Loading 0:  94%|█████████▍| 341/363 [00:17<00:01, 15.83it/s]
Loading 0:  95%|█████████▌| 346/363 [00:17<00:00, 19.74it/s]
Loading 0:  96%|█████████▋| 350/363 [00:17<00:00, 22.08it/s]
Loading 0:  98%|█████████▊| 355/363 [00:17<00:00, 26.24it/s]
Loading 0:  99%|█████████▉| 359/363 [00:17<00:00, 27.46it/s]
                                                            
Job alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer completed after 114.47s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-base-dpo-v2-mkmlizer
Pipeline stage MKMLizer completed in 114.92s
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-v2
Waiting for inference service alexxi19-ft-v1-nemo-base-dpo-v2 to be ready
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service alexxi19-ft-v1-nemo-base-dpo-v2 ready after 190.74856638908386s
Pipeline stage MKMLDeployer completed in 191.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6993870735168457s
Received healthy response to inference request in 1.7344565391540527s
Received healthy response to inference request in 1.7801706790924072s
Received healthy response to inference request in 1.6987533569335938s
Received healthy response to inference request in 2.147580862045288s
5 requests
0 failed requests
5th percentile: 1.7058939933776855
10th percentile: 1.7130346298217773
20th percentile: 1.727315902709961
30th percentile: 1.7435993671417236
40th percentile: 1.7618850231170655
50th percentile: 1.7801706790924072
60th percentile: 1.9271347522735596
70th percentile: 2.074098825454712
80th percentile: 2.2579421043395995
90th percentile: 2.478664588928223
95th percentile: 2.5890258312225343
99th percentile: 2.6773148250579832
mean time: 2.0120697021484375
Pipeline stage StressChecker completed in 11.30s
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 0.69s
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 0.68s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-base-dpo_v2 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 2561.52s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-base-dpo_v2 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-base-dpo_v2 status is now torndown due to DeploymentManager action