chaiml-mistral-nemo-dpo-_4126

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_4126_v2

model_name: chaiml-mistral-nemo-dpo-_4126_v2

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-12T08:49:32+00:00

num_battles: 7649

num_wins: 3667

celo_rating: 1252.17

family_friendly_score: 0.5862

family_friendly_standard_error: 0.006965192890365636

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

latencies: [{'batch_size': 1, 'throughput': 0.6360379497125536, 'latency_mean': 1.5721455919742584, 'latency_p50': 1.5846182107925415, 'latency_p90': 1.7279273986816406}, {'batch_size': 3, 'throughput': 1.2642152037221344, 'latency_mean': 2.3577580511569978, 'latency_p50': 2.3587831258773804, 'latency_p90': 2.6298196792602537}, {'batch_size': 5, 'throughput': 1.6021597075453775, 'latency_mean': 3.1065002131462096, 'latency_p50': 3.109686493873596, 'latency_p90': 3.421057438850403}, {'batch_size': 6, 'throughput': 1.6947081786553655, 'latency_mean': 3.520135010480881, 'latency_p50': 3.5211278200149536, 'latency_p90': 3.923132371902466}, {'batch_size': 8, 'throughput': 1.8777184008415724, 'latency_mean': 4.234512547254562, 'latency_p50': 4.245129823684692, 'latency_p90': 4.758463573455811}, {'batch_size': 10, 'throughput': 1.94855758073216, 'latency_mean': 5.098592417240143, 'latency_p50': 5.148420929908752, 'latency_p90': 5.7330138206481935}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_4126_v2

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_baseline_albert_241210_v2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.76

us_pacific_date: 2024-12-12

win_ratio: 0.47940907308144853

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-4126-v2-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-4126-v2-mkmlizer to finish
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: Downloaded to shared memory in 50.082s
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp91u5voxy, device:0
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: quantized model in 37.626s
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_baseline_albert_241210_v2 in 87.708s
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4126-v2
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4126-v2/config.json
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4126-v2/special_tokens_map.json
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4126-v2/tokenizer_config.json
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4126-v2/tokenizer.json
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4126-v2/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-4126-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.58it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 45.37it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 45.96it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 36.66it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.27it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 43.63it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:07, 42.16it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:06, 46.08it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:06, 44.41it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:06, 47.95it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:11, 25.70it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 32.82it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 33.99it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:08, 34.04it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 35.96it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 32.11it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 39.18it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 39.56it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 43.79it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 38.30it/s]
Loading 0:  33%|███▎      | 119/363 [00:03<00:06, 38.56it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 44.06it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 42.82it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 42.20it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 31.58it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 32.57it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:06, 32.16it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 38.22it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 38.43it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 39.95it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 42.40it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 36.85it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 44.71it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 44.56it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 44.45it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:03, 41.42it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 40.88it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 45.97it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 43.14it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 44.09it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 29.86it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 30.13it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 37.31it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 38.62it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 38.93it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 44.12it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 44.45it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 35.24it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 40.92it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:02, 40.72it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 41.31it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 42.74it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:02, 34.65it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 39.22it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:24,  2.42it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:17,  3.12it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.05it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:06,  6.39it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:05,  7.94it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03, 11.13it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:02, 14.28it/s]
Loading 0:  93%|█████████▎| 339/363 [00:15<00:01, 16.36it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 22.72it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 25.99it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 29.64it/s]
Loading 0:  99%|█████████▉| 361/363 [00:16<00:00, 32.31it/s]
                                                            
Job chaiml-mistral-nemo-dpo-4126-v2-mkmlizer completed after 115.57s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-4126-v2-mkmlizer
Pipeline stage MKMLizer completed in 116.10s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.22s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-dpo-4126-v2
Waiting for inference service chaiml-mistral-nemo-dpo-4126-v2 to be ready
Inference service chaiml-mistral-nemo-dpo-4126-v2 ready after 191.5879671573639s
Pipeline stage MKMLDeployer completed in 192.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6908161640167236s
Received healthy response to inference request in 0.9865546226501465s
Received healthy response to inference request in 0.7770047187805176s
Received healthy response to inference request in 1.3033051490783691s
Received healthy response to inference request in 1.2098228931427002s
5 requests
0 failed requests
5th percentile: 0.8189146995544434
10th percentile: 0.8608246803283691
20th percentile: 0.9446446418762207
30th percentile: 1.0312082767486572
40th percentile: 1.1205155849456787
50th percentile: 1.2098228931427002
60th percentile: 1.2472157955169678
70th percentile: 1.2846086978912354
80th percentile: 1.3808073520660402
90th percentile: 1.535811758041382
95th percentile: 1.6133139610290526
99th percentile: 1.6753157234191893
mean time: 1.1935007095336914
Pipeline stage StressChecker completed in 17.37s
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 2.13s
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 2.05s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_4126_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 2370.99s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_4126_v2 status is now inactive due to auto deactivation removed underperforming models