chaiml-mistral-nemo-dpo-_2408

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_2408_v2

model_name: chaiml-mistral-nemo-dpo-_2408_v2

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-19T18:07:13+00:00

num_battles: 14053

num_wins: 6921

celo_rating: 1258.68

family_friendly_score: 0.5744

family_friendly_standard_error: 0.006992347817435857

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-6240

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6377236488606653, 'latency_mean': 1.5679844427108764, 'latency_p50': 1.5630027055740356, 'latency_p90': 1.7277475118637085}, {'batch_size': 3, 'throughput': 1.2634501353859346, 'latency_mean': 2.3686728048324586, 'latency_p50': 2.379761815071106, 'latency_p90': 2.618564414978027}, {'batch_size': 5, 'throughput': 1.5920946666944473, 'latency_mean': 3.1289260923862456, 'latency_p50': 3.1407694816589355, 'latency_p90': 3.525579333305359}, {'batch_size': 6, 'throughput': 1.6973957646444664, 'latency_mean': 3.5183738446235657, 'latency_p50': 3.522339940071106, 'latency_p90': 3.951898646354675}, {'batch_size': 8, 'throughput': 1.848744363584123, 'latency_mean': 4.312455579042434, 'latency_p50': 4.337377429008484, 'latency_p90': 4.850765991210937}, {'batch_size': 10, 'throughput': 1.9316510499999613, 'latency_mean': 5.154094696044922, 'latency_p50': 5.1108152866363525, 'latency_p90': 5.864410066604615}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_2408_v2

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-6240

model_size: 13B

ranking_group: single

throughput_3p7s: 1.75

us_pacific_date: 2024-12-19

win_ratio: 0.49249270618373303

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-2408-v2-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-2408-v2-mkmlizer to finish
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: Downloaded to shared memory in 33.441s
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplrxo3olt, device:0
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: quantized model in 36.356s
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-6240 in 69.797s
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2408-v2
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2408-v2/config.json
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2408-v2/special_tokens_map.json
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2408-v2/tokenizer_config.json
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2408-v2/tokenizer.json
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2408-v2/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-2408-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.09it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.53it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.33it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.37it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.59it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.79it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.43it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.53it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 48.89it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 44.70it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.79it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 36.38it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 38.44it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:07, 40.04it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 42.20it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 35.89it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 42.51it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 42.02it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 43.59it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 36.91it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:06, 36.27it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 43.36it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.78it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 43.00it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 44.43it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.67it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 27.60it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.43it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 37.36it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 39.40it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 41.60it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 36.08it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 43.87it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 44.56it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 44.95it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 42.49it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 41.68it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 45.74it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 44.70it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 46.00it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:04, 28.82it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 30.98it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 39.61it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 38.82it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 38.42it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 42.83it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 43.26it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 44.42it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 40.01it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 39.79it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 45.06it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 42.52it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 41.40it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 42.45it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:23,  2.51it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:17,  3.24it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.22it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  7.01it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.40it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.88it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.54it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:00, 20.05it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 21.41it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 28.24it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 30.69it/s]
                                                            
Job chaiml-mistral-nemo-dpo-2408-v2-mkmlizer completed after 94.22s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-2408-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.76s
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-2408-v2
Waiting for inference service chaiml-mistral-nemo-dpo-2408-v2 to be ready
Inference service chaiml-mistral-nemo-dpo-2408-v2 ready after 260.91003942489624s
Pipeline stage MKMLDeployer completed in 261.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7801792621612549s
Received healthy response to inference request in 0.8917415142059326s
Received healthy response to inference request in 1.5171527862548828s
Received healthy response to inference request in 0.7612886428833008s
Received healthy response to inference request in 1.274317979812622s
5 requests
0 failed requests
5th percentile: 0.7873792171478271
10th percentile: 0.8134697914123535
20th percentile: 0.8656509399414063
30th percentile: 0.9682568073272705
40th percentile: 1.1212873935699463
50th percentile: 1.274317979812622
60th percentile: 1.3714519023895264
70th percentile: 1.4685858249664305
80th percentile: 1.5697580814361574
90th percentile: 1.674968671798706
95th percentile: 1.7275739669799803
99th percentile: 1.7696582031249999
mean time: 1.2449360370635987
Pipeline stage StressChecker completed in 7.75s
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 2.31s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Connection pool is full, discarding connection: %s. Connection pool size: %s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.03s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_2408_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-nemo-dpo-2408-v2-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-2408-v2-profiler to be ready
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 2918.87s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_2408_v2 status is now inactive due to auto deactivation removed underperforming models