developer_uid: rirv938
submission_id: rirv938-mistral-24b-dpo_93661_v1
model_name: rirv938-mistral-24b-dpo_93661_v1
model_group: rirv938/mistral_24b_dpo_
status: torndown
timestamp: 2025-02-23T06:20:49+00:00
num_battles: 10593
num_wins: 5340
celo_rating: 1280.23
family_friendly_score: 0.6184000000000001
family_friendly_standard_error: 0.006869955458370891
submission_type: basic
model_repo: rirv938/mistral_24b_dpo_40k_95w_pref_3750_instruct_v2
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.389958674400628, 'latency_mean': 2.5642797780036926, 'latency_p50': 2.5675852298736572, 'latency_p90': 2.8449730396270754}, {'batch_size': 3, 'throughput': 0.8045516375467849, 'latency_mean': 3.708811320066452, 'latency_p50': 3.664621949195862, 'latency_p90': 4.125813317298889}, {'batch_size': 5, 'throughput': 1.052794399768657, 'latency_mean': 4.720758869647979, 'latency_p50': 4.725116014480591, 'latency_p90': 5.280927777290344}, {'batch_size': 6, 'throughput': 1.1310044924184737, 'latency_mean': 5.265554352998733, 'latency_p50': 5.308176875114441, 'latency_p90': 5.9166247844696045}, {'batch_size': 10, 'throughput': 1.3130056165786306, 'latency_mean': 7.559870117902756, 'latency_p50': 7.587582111358643, 'latency_p90': 8.470843505859374}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-dpo_93661_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_dpo_40k_95w_pref_3750_instruct_v2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.81
us_pacific_date: 2025-02-22
win_ratio: 0.5041064854148967
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '###', 'You:'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{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 rirv938-mistral-24b-dpo-93661-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-93661-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: Downloaded to shared memory in 251.878s
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe1313ntt, device:0
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: quantized model in 65.894s
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_40k_95w_pref_3750_instruct_v2 in 317.773s
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-93661-v1
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-93661-v1/config.json
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-93661-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-93661-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-93661-v1/tokenizer.json
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-93661-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-93661-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-93661-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.03it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.64it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.07it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.31it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:27, 12.84it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.38it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.12it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 18.76it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.21it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.34it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:21, 15.30it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:24, 13.41it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:25, 12.36it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:19, 16.01it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:16, 19.30it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:23, 12.95it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:24, 12.50it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:22, 13.51it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:27, 11.11it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 17.15it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.46it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:20, 14.09it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:19, 14.58it/s]
Loading 0:  21%|██        | 76/363 [00:05<00:22, 12.97it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:22, 12.50it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 16.78it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.90it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:19, 14.35it/s]
Loading 0:  25%|██▌       | 92/363 [00:06<00:18, 14.91it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.41it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 20.83it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 18.92it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:19, 13.27it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:21, 11.76it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:22, 11.33it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:20, 12.34it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:24, 10.37it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:15, 16.00it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:12, 19.28it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:17, 13.84it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.29it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 14.15it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:20, 11.30it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:13, 16.91it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:11, 19.75it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:16, 13.44it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:16, 12.83it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:15, 13.72it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:19, 10.99it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 16.40it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:10, 19.67it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 13.49it/s]
Loading 0:  45%|████▍     | 163/363 [00:11<00:15, 13.13it/s]
Loading 0:  45%|████▌     | 165/363 [00:11<00:14, 14.04it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:17, 11.49it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 17.34it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 20.68it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:12, 14.64it/s]
Loading 0:  50%|█████     | 182/363 [00:12<00:11, 15.14it/s]
Loading 0:  51%|█████     | 184/363 [00:12<00:13, 13.43it/s]
Loading 0:  51%|█████     | 186/363 [00:12<00:14, 12.46it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 15.83it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 18.91it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:12, 13.51it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:12, 13.09it/s]
Loading 0:  55%|█████▌    | 201/363 [00:29<05:05,  1.88s/it]
Loading 0:  56%|█████▌    | 203/363 [00:29<03:51,  1.45s/it]
Loading 0:  57%|█████▋    | 207/363 [00:29<02:13,  1.17it/s]
Loading 0:  58%|█████▊    | 210/363 [00:29<01:32,  1.65it/s]
Loading 0:  59%|█████▊    | 213/363 [00:29<01:06,  2.24it/s]
Loading 0:  59%|█████▉    | 215/363 [00:30<00:54,  2.72it/s]
Loading 0:  60%|█████▉    | 217/363 [00:30<00:43,  3.35it/s]
Loading 0:  60%|██████    | 219/363 [00:30<00:33,  4.25it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:30,  4.69it/s]
Loading 0:  62%|██████▏   | 226/363 [00:30<00:16,  8.20it/s]
Loading 0:  63%|██████▎   | 230/363 [00:31<00:11, 11.33it/s]
Loading 0:  64%|██████▍   | 233/363 [00:31<00:12, 10.22it/s]
Loading 0:  65%|██████▍   | 235/363 [00:31<00:12, 10.61it/s]
Loading 0:  65%|██████▌   | 237/363 [00:31<00:10, 11.73it/s]
Loading 0:  66%|██████▌   | 239/363 [00:31<00:11, 10.39it/s]
Loading 0:  67%|██████▋   | 245/363 [00:32<00:06, 17.85it/s]
Loading 0:  69%|██████▊   | 249/363 [00:32<00:06, 16.97it/s]
Loading 0:  69%|██████▉   | 252/363 [00:32<00:08, 13.29it/s]
Loading 0:  70%|███████   | 255/363 [00:32<00:07, 15.22it/s]
Loading 0:  71%|███████   | 258/363 [00:33<00:07, 14.08it/s]
Loading 0:  72%|███████▏  | 262/363 [00:33<00:05, 17.87it/s]
Loading 0:  73%|███████▎  | 266/363 [00:33<00:04, 21.19it/s]
Loading 0:  74%|███████▍  | 269/363 [00:33<00:06, 15.04it/s]
Loading 0:  75%|███████▍  | 272/363 [00:33<00:05, 15.60it/s]
Loading 0:  75%|███████▌  | 274/363 [00:33<00:06, 14.05it/s]
Loading 0:  76%|███████▌  | 276/363 [00:34<00:06, 13.61it/s]
Loading 0:  77%|███████▋  | 280/363 [00:34<00:04, 18.28it/s]
Loading 0:  78%|███████▊  | 284/363 [00:34<00:03, 22.53it/s]
Loading 0:  79%|███████▉  | 287/363 [00:34<00:04, 15.72it/s]
Loading 0:  80%|███████▉  | 290/363 [00:34<00:04, 16.50it/s]
Loading 0:  81%|████████  | 293/363 [00:35<00:05, 12.84it/s]
Loading 0:  82%|████████▏ | 298/363 [00:35<00:03, 18.35it/s]
Loading 0:  83%|████████▎ | 302/363 [00:35<00:02, 21.80it/s]
Loading 0:  84%|████████▍ | 305/363 [00:35<00:03, 15.86it/s]
Loading 0:  85%|████████▍ | 308/363 [00:35<00:03, 16.51it/s]
Loading 0:  86%|████████▌ | 311/363 [00:36<00:03, 13.10it/s]
Loading 0:  87%|████████▋ | 316/363 [00:36<00:02, 18.42it/s]
Loading 0:  88%|████████▊ | 320/363 [00:36<00:01, 22.05it/s]
Loading 0:  89%|████████▉ | 324/363 [00:36<00:02, 14.28it/s]
Loading 0:  90%|█████████ | 327/363 [00:37<00:02, 16.07it/s]
Loading 0:  91%|█████████ | 330/363 [00:37<00:02, 14.71it/s]
Loading 0:  92%|█████████▏| 334/363 [00:37<00:01, 18.52it/s]
Loading 0:  93%|█████████▎| 338/363 [00:37<00:01, 22.13it/s]
Loading 0:  94%|█████████▍| 341/363 [00:37<00:01, 15.28it/s]
Loading 0:  95%|█████████▍| 344/363 [00:38<00:01, 15.77it/s]
Loading 0:  96%|█████████▌| 347/363 [00:38<00:01, 12.26it/s]
Loading 0:  97%|█████████▋| 352/363 [00:38<00:00, 17.38it/s]
Loading 0:  98%|█████████▊| 356/363 [00:38<00:00, 20.87it/s]
Loading 0:  99%|█████████▉| 359/363 [00:46<00:02,  1.54it/s]
Loading 0: 100%|█████████▉| 362/363 [00:46<00:00,  1.99it/s]
                                                            

Job rirv938-mistral-24b-dpo-93661-v1-mkmlizer completed after 349.82s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-93661-v1-mkmlizer
Pipeline stage MKMLizer completed in 350.32s
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 rirv938-mistral-24b-dpo-93661-v1
Waiting for inference service rirv938-mistral-24b-dpo-93661-v1 to be ready
Inference service rirv938-mistral-24b-dpo-93661-v1 ready after 240.89975953102112s
Pipeline stage MKMLDeployer completed in 241.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.833505868911743s
Received healthy response to inference request in 1.7618937492370605s
Received healthy response to inference request in 1.6927146911621094s
Received healthy response to inference request in 1.568908452987671s
Received healthy response to inference request in 1.5847206115722656s
5 requests
0 failed requests
5th percentile: 1.5720708847045899
10th percentile: 1.5752333164215089
20th percentile: 1.5815581798553466
30th percentile: 1.6063194274902344
40th percentile: 1.6495170593261719
50th percentile: 1.6927146911621094
60th percentile: 1.7203863143920899
70th percentile: 1.7480579376220704
80th percentile: 1.9762161731719972
90th percentile: 2.4048610210418704
95th percentile: 2.6191834449768066
99th percentile: 2.790641384124756
mean time: 1.88834867477417
Pipeline stage StressChecker completed in 10.66s
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 0.61s
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 0.58s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_93661_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5332.21s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_93661_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_93661_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1