chaiml-mistral-nemo-dpo-_4126

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_4126_v1

model_name: chaiml-mistral-nemo-dpo-_4126_v1

model_group: ChaiML/mistral_nemo_dpo_

status: torndown

timestamp: 2024-12-10T14:51:42+00:00

num_battles: 17658

num_wins: 8523

celo_rating: 1251.45

family_friendly_score: 0.5844

family_friendly_standard_error: 0.006969600275482089

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_baseline_albert_241210_v2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6480673677801333, 'latency_mean': 1.5429886412620544, 'latency_p50': 1.5357191562652588, 'latency_p90': 1.7000621318817137}, {'batch_size': 4, 'throughput': 1.5035794193365577, 'latency_mean': 2.6547464299201966, 'latency_p50': 2.6662909984588623, 'latency_p90': 3.011246752738953}, {'batch_size': 5, 'throughput': 1.643603984070627, 'latency_mean': 3.0311242818832396, 'latency_p50': 3.024962306022644, 'latency_p90': 3.401399111747742}, {'batch_size': 8, 'throughput': 1.9261772724974666, 'latency_mean': 4.134368166923523, 'latency_p50': 4.123941659927368, 'latency_p90': 4.668057775497436}, {'batch_size': 10, 'throughput': 2.0150852695588832, 'latency_mean': 4.917546761035919, 'latency_p50': 4.916728854179382, 'latency_p90': 5.555880546569824}, {'batch_size': 12, 'throughput': 2.0695343793120733, 'latency_mean': 5.7331789469718935, 'latency_p50': 5.671672821044922, 'latency_p90': 6.646915030479431}, {'batch_size': 15, 'throughput': 2.130513308425388, 'latency_mean': 6.969917675256729, 'latency_p50': 6.994466543197632, 'latency_p90': 8.06242413520813}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_4126_v1

is_internal_developer: False

language_model: ChaiML/mistral_nemo_dpo_baseline_albert_241210_v2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.84

us_pacific_date: 2024-12-10

win_ratio: 0.48267074413863403

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'User:', '<|eot_id|>', '####', 'You:', '</s>', '<|im_end|>', 'Bot:'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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-mistral-nemo-dpo-4126-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-4126-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: Downloaded to shared memory in 47.709s
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7hhy11l9, device:0
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: quantized model in 36.920s
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_baseline_albert_241210_v2 in 84.629s
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4126-v1
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4126-v1/config.json
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4126-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4126-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4126-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-4126-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 25.89it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 42.09it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 41.59it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:07, 43.38it/s]
Loading 0:   8%|▊         | 28/363 [00:00<00:07, 42.70it/s]
Loading 0:   9%|▉         | 33/363 [00:00<00:07, 41.48it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:06, 47.59it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:06, 45.37it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:07, 44.10it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:06, 48.11it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:09, 30.54it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:09, 31.17it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 36.09it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 37.91it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 37.69it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 43.40it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 42.10it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.27it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 42.47it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 45.74it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:06, 40.46it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:05, 41.30it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 35.39it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 43.10it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 44.56it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:08, 27.10it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.44it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 34.85it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.44it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.21it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 39.37it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 40.30it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 45.25it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 44.81it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:03, 44.46it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 48.26it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:03, 46.60it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:03, 45.46it/s]
Loading 0:  60%|██████    | 219/363 [00:05<00:02, 48.91it/s]
Loading 0:  62%|██████▏   | 224/363 [00:05<00:04, 33.60it/s]
Loading 0:  63%|██████▎   | 229/363 [00:05<00:03, 33.59it/s]
Loading 0:  65%|██████▍   | 235/363 [00:05<00:03, 35.72it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 35.21it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:02, 42.14it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 41.60it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 41.80it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 43.83it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 38.38it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 45.71it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 43.87it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 43.95it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 41.94it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 40.30it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 41.93it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:24,  2.38it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:17,  3.10it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.05it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.79it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  9.22it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:02, 11.74it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.47it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 20.02it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.02it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 29.09it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 32.27it/s]
                                                            
Job chaiml-mistral-nemo-dpo-4126-v1-mkmlizer completed after 105.33s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-4126-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.86s
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-mistral-nemo-dpo-4126-v1
Waiting for inference service chaiml-mistral-nemo-dpo-4126-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-mistral-nemo-dpo-4126-v1 ready after 180.719970703125s
Pipeline stage MKMLDeployer completed in 181.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.880206823348999s
Received healthy response to inference request in 0.8722405433654785s
Received healthy response to inference request in 1.7793772220611572s
Received healthy response to inference request in 1.180629014968872s
Received healthy response to inference request in 1.233351469039917s
5 requests
0 failed requests
5th percentile: 0.9339182376861572
10th percentile: 0.9955959320068359
20th percentile: 1.1189513206481934
30th percentile: 1.191173505783081
40th percentile: 1.2122624874114991
50th percentile: 1.233351469039917
60th percentile: 1.4517617702484131
70th percentile: 1.670172071456909
80th percentile: 1.7995431423187256
90th percentile: 1.8398749828338623
95th percentile: 1.8600409030914307
99th percentile: 1.8761736392974853
mean time: 1.3891610145568847
Pipeline stage StressChecker completed in 8.27s
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 2.59s
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 2.14s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_4126_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 2453.13s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_4126_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-nemo-dpo-_4126_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_4126_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_4126_v1 status is now torndown due to DeploymentManager action