chaiml-mistral-nemo-dpo-_8786

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_8786_v2

model_name: chaiml-mistral-nemo-dpo-_8786_v2

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-17T18:55:13+00:00

num_battles: 7719

num_wins: 3738

celo_rating: 1244.68

family_friendly_score: 0.5816

family_friendly_standard_error: 0.006976266049972578

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-624

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6284300740737776, 'latency_mean': 1.5911847734451294, 'latency_p50': 1.6085888147354126, 'latency_p90': 1.7523971796035767}, {'batch_size': 3, 'throughput': 1.2617385903103298, 'latency_mean': 2.366035063266754, 'latency_p50': 2.3692396879196167, 'latency_p90': 2.6644673585891723}, {'batch_size': 5, 'throughput': 1.600666741958191, 'latency_mean': 3.115011873245239, 'latency_p50': 3.111545443534851, 'latency_p90': 3.491830086708069}, {'batch_size': 6, 'throughput': 1.7200061098029684, 'latency_mean': 3.465027182102203, 'latency_p50': 3.4625295400619507, 'latency_p90': 3.954343342781067}, {'batch_size': 8, 'throughput': 1.8758416007552805, 'latency_mean': 4.232475420236588, 'latency_p50': 4.228862643241882, 'latency_p90': 4.847207808494568}, {'batch_size': 10, 'throughput': 1.9487766296079023, 'latency_mean': 5.089077268838882, 'latency_p50': 5.078500390052795, 'latency_p90': 5.732170510292053}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_8786_v2

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-624

model_size: 13B

ranking_group: single

throughput_3p7s: 1.79

us_pacific_date: 2024-12-17

win_ratio: 0.4842596191216479

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-8786-v2-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-8786-v2-mkmlizer to finish
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: Downloaded to shared memory in 35.478s
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4s7qn8tu, device:0
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: quantized model in 38.079s
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-624 in 73.557s
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8786-v2
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8786-v2/config.json
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8786-v2/special_tokens_map.json
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8786-v2/tokenizer_config.json
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8786-v2/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-8786-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 25.86it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 42.36it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 41.43it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 42.58it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 44.45it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 34.82it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:07, 43.06it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:07, 42.79it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 43.50it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 44.30it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:06, 45.78it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:11, 25.76it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 33.33it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 35.34it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 37.13it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 37.99it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 31.59it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 37.97it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 37.98it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 40.26it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:07, 35.20it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 36.19it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 44.15it/s]
Loading 0:  36%|███▌      | 131/363 [00:03<00:05, 44.69it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:05, 38.43it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 32.46it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 33.17it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:06, 32.46it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:05, 39.22it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:05, 39.84it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 40.25it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 46.14it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 44.55it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 41.92it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 46.25it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 45.87it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 38.11it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 45.67it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 43.63it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 33.76it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 33.21it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 32.29it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 38.83it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 39.02it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 38.71it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 43.58it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 43.54it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 44.80it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 42.06it/s]
Loading 0:  76%|███████▌  | 276/363 [00:07<00:02, 40.31it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 45.26it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 46.30it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:01, 37.53it/s]
Loading 0:  83%|████████▎ | 300/363 [00:07<00:01, 44.80it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:22,  2.54it/s]
Loading 0:  85%|████████▌ | 309/363 [00:14<00:16,  3.23it/s]
Loading 0:  86%|████████▌ | 313/363 [00:14<00:12,  4.16it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:06,  6.49it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:04,  8.88it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:02, 11.23it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 15.76it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 19.03it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 20.43it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 27.22it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 29.92it/s]
                                                            
Job chaiml-mistral-nemo-dpo-8786-v2-mkmlizer completed after 105.27s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-8786-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.80s
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-8786-v2
Waiting for inference service chaiml-mistral-nemo-dpo-8786-v2 to be ready
Inference service chaiml-mistral-nemo-dpo-8786-v2 ready after 231.7125744819641s
Pipeline stage MKMLDeployer completed in 232.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5279791355133057s
Received healthy response to inference request in 1.1961121559143066s
Received healthy response to inference request in 0.5743012428283691s
Received healthy response to inference request in 1.2315106391906738s
Received healthy response to inference request in 1.3396716117858887s
5 requests
0 failed requests
5th percentile: 0.6986634254455566
10th percentile: 0.8230256080627442
20th percentile: 1.0717499732971192
30th percentile: 1.2031918525695802
40th percentile: 1.217351245880127
50th percentile: 1.2315106391906738
60th percentile: 1.2747750282287598
70th percentile: 1.3180394172668457
80th percentile: 1.377333116531372
90th percentile: 1.452656126022339
95th percentile: 1.4903176307678223
99th percentile: 1.520446834564209
mean time: 1.1739149570465088
Pipeline stage StressChecker completed in 7.28s
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 2.27s
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-_8786_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 2840.83s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_8786_v2 status is now inactive due to auto deactivation removed underperforming models