chaiml-mistral-nemo-dpo-_7200

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_7200_v3

model_name: chaiml-mistral-nemo-dpo-_7200_v3

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-20T23:14:18+00:00

num_battles: 8992

num_wins: 4268

celo_rating: 1228.64

family_friendly_score: 0.5988

family_friendly_standard_error: 0.006931645692041681

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-138

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6335824055685736, 'latency_mean': 1.5782300078868865, 'latency_p50': 1.5804775953292847, 'latency_p90': 1.7425605297088622}, {'batch_size': 3, 'throughput': 1.2860254598120349, 'latency_mean': 2.322533893585205, 'latency_p50': 2.31200635433197, 'latency_p90': 2.550257611274719}, {'batch_size': 5, 'throughput': 1.6021539455823277, 'latency_mean': 3.1057092082500457, 'latency_p50': 3.1197372674942017, 'latency_p90': 3.456447219848633}, {'batch_size': 6, 'throughput': 1.7241288699003738, 'latency_mean': 3.4586332130432127, 'latency_p50': 3.468533158302307, 'latency_p90': 3.8581234216690063}, {'batch_size': 8, 'throughput': 1.8611026222268874, 'latency_mean': 4.253231470584869, 'latency_p50': 4.2557443380355835, 'latency_p90': 4.840054082870483}, {'batch_size': 10, 'throughput': 1.9414312461153649, 'latency_mean': 5.11071408033371, 'latency_p50': 5.08834183216095, 'latency_p90': 5.867267084121704}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_7200_v3

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-138

model_size: 13B

ranking_group: single

throughput_3p7s: 1.79

us_pacific_date: 2024-12-20

win_ratio: 0.474644128113879

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', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], '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-7200-v3-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-7200-v3-mkmlizer to finish
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: Downloaded to shared memory in 36.109s
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpd0gtwq7e, device:0
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: quantized model in 35.756s
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-138 in 71.866s
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-7200-v3
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-7200-v3/tokenizer.json
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-7200-v3/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-7200-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.09it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 46.54it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 43.14it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.53it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 47.12it/s]
Loading 0:  10%|▉         | 36/363 [00:00<00:06, 47.24it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:08, 38.23it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 46.75it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:07, 43.61it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:07, 42.88it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 29.02it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 35.46it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 38.10it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 34.86it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 42.97it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 42.03it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.28it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 50.05it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 46.72it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 45.59it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 45.72it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 45.93it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:05, 42.87it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:05, 37.58it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:05, 37.68it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:05, 35.85it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 43.38it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 44.30it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 44.45it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:03, 48.97it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 46.20it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 44.14it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 49.39it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 45.86it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 43.90it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 49.40it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 47.08it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 34.13it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 34.57it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.85it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 39.67it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 40.10it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 39.00it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 43.43it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 43.36it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 44.37it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 43.09it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 43.04it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 47.89it/s]
Loading 0:  79%|███████▉  | 288/363 [00:06<00:01, 48.16it/s]
Loading 0:  81%|████████  | 293/363 [00:06<00:01, 39.85it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 49.08it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:19,  2.84it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:13,  3.76it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.82it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.76it/s]
Loading 0:  91%|█████████▏| 332/363 [00:14<00:03, 10.27it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.55it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 17.07it/s]
Loading 0:  96%|█████████▋| 350/363 [00:14<00:00, 21.28it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 26.30it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.76it/s]
                                                            
Job chaiml-mistral-nemo-dpo-7200-v3-mkmlizer completed after 93.9s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-7200-v3-mkmlizer
Pipeline stage MKMLizer completed in 94.40s
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-mistral-nemo-dpo-7200-v3
Waiting for inference service chaiml-mistral-nemo-dpo-7200-v3 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
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-7200-v3 ready after 260.9299433231354s
Pipeline stage MKMLDeployer completed in 261.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6875474452972412s
Received healthy response to inference request in 1.3069825172424316s
Received healthy response to inference request in 0.6617870330810547s
Received healthy response to inference request in 1.7536990642547607s
Received healthy response to inference request in 1.3389348983764648s
5 requests
0 failed requests
5th percentile: 0.7908261299133301
10th percentile: 0.9198652267456056
20th percentile: 1.1779434204101562
30th percentile: 1.3133729934692382
40th percentile: 1.3261539459228515
50th percentile: 1.3389348983764648
60th percentile: 1.4783799171447753
70th percentile: 1.6178249359130858
80th percentile: 1.7007777690887451
90th percentile: 1.727238416671753
95th percentile: 1.7404687404632568
99th percentile: 1.7510529994964599
mean time: 1.3497901916503907
Pipeline stage StressChecker completed in 8.63s
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 0.79s
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-mistral-nemo-dpo-_7200_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 2032.58s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_7200_v3 status is now inactive due to auto deactivation removed underperforming models