alexdaoud-trainer-famon_50949

developer_uid: dtnewman

submission_id: alexdaoud-trainer-famon_50949_v1

model_name: alexdaoud-trainer-famon_50949_v1

model_group: alexdaoud/trainer_famon_

status: torndown

timestamp: 2025-02-26T22:46:45+00:00

num_battles: 7786

num_wins: 3727

celo_rating: 1245.1

family_friendly_score: 0.5808

family_friendly_standard_error: 0.006978128115762852

submission_type: basic

model_repo: alexdaoud/trainer_famon_2025-02-26-checkpoint-1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.606712202594688, 'latency_mean': 1.6481685709953309, 'latency_p50': 1.6509102582931519, 'latency_p90': 1.8247111082077025}, {'batch_size': 3, 'throughput': 1.0988570935629878, 'latency_mean': 2.7232372331619263, 'latency_p50': 2.7183808088302612, 'latency_p90': 3.0535077333450316}, {'batch_size': 5, 'throughput': 1.329791388116792, 'latency_mean': 3.7387173175811768, 'latency_p50': 3.7235476970672607, 'latency_p90': 4.146942186355591}, {'batch_size': 6, 'throughput': 1.3899549394787676, 'latency_mean': 4.294330282211304, 'latency_p50': 4.267519116401672, 'latency_p90': 4.8676938772201535}, {'batch_size': 8, 'throughput': 1.4536068531341002, 'latency_mean': 5.4698438501358035, 'latency_p50': 5.516161203384399, 'latency_p90': 6.169451904296875}, {'batch_size': 10, 'throughput': 1.4829572337505088, 'latency_mean': 6.702261453866958, 'latency_p50': 6.697357177734375, 'latency_p90': 7.528265476226807}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: alexdaoud-trainer-famon_50949_v1

ineligible_reason: num_battles<10000

is_internal_developer: False

language_model: alexdaoud/trainer_famon_2025-02-26-checkpoint-1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-02-26

win_ratio: 0.47867968147957873

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 alexdaoud-trainer-famon-50949-v1-mkmlizer
Waiting for job on alexdaoud-trainer-famon-50949-v1-mkmlizer to finish
alexdaoud-trainer-famon-50949-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║     _____            __           __                                ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║       /___/                                                         ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║  https://mk1.ai                                                     ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║  belonging to:                                                      ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║  Chai Research Corp.                                                ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-famon-50949-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission nischaydnk-exp15-mistra_19652_v2: HTTPConnectionPool(host='nischaydnk-exp15-mistra-19652-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
alexdaoud-trainer-famon-50949-v1-mkmlizer: Downloaded to shared memory in 48.796s
alexdaoud-trainer-famon-50949-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf3lsatnu, device:0
alexdaoud-trainer-famon-50949-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexdaoud-trainer-famon-50949-v1-mkmlizer: quantized model in 37.658s
alexdaoud-trainer-famon-50949-v1-mkmlizer: Processed model alexdaoud/trainer_famon_2025-02-26-checkpoint-1 in 86.455s
alexdaoud-trainer-famon-50949-v1-mkmlizer: creating bucket guanaco-mkml-models
alexdaoud-trainer-famon-50949-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexdaoud-trainer-famon-50949-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexdaoud-trainer-famon-50949-v1
alexdaoud-trainer-famon-50949-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexdaoud-trainer-famon-50949-v1/config.json
alexdaoud-trainer-famon-50949-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexdaoud-trainer-famon-50949-v1/special_tokens_map.json
alexdaoud-trainer-famon-50949-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexdaoud-trainer-famon-50949-v1/tokenizer_config.json
alexdaoud-trainer-famon-50949-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexdaoud-trainer-famon-50949-v1/tokenizer.json
alexdaoud-trainer-famon-50949-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexdaoud-trainer-famon-50949-v1/flywheel_model.0.safetensors
alexdaoud-trainer-famon-50949-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.88it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 42.73it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 41.57it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 41.77it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 43.93it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.21it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:07, 43.48it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:07, 42.87it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 42.57it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:07, 43.15it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:06, 44.64it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:12, 24.73it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:09, 32.19it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 34.57it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 36.58it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 39.14it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.81it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 40.68it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 40.95it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 42.63it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:07, 35.62it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.96it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 43.34it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.01it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.45it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 44.12it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 25.92it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 26.56it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 34.61it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.28it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.29it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.41it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.59it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 41.16it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 40.93it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 41.26it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 42.72it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 35.06it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 41.33it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 40.42it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 41.61it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 25.74it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 28.00it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.18it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 36.36it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 37.40it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 39.17it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 32.71it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 39.32it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 39.57it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 40.02it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 41.62it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 35.27it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 41.80it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 41.24it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 42.35it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:23,  2.42it/s]
Loading 0:  85%|████████▌ | 310/363 [00:15<00:16,  3.13it/s]
Loading 0:  87%|████████▋ | 314/363 [00:15<00:11,  4.10it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:07,  6.11it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:04,  8.52it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:03, 10.35it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:01, 15.25it/s]
Loading 0:  94%|█████████▍| 342/363 [00:15<00:01, 18.49it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 21.30it/s]
Loading 0:  97%|█████████▋| 352/363 [00:16<00:00, 25.04it/s]
Loading 0:  98%|█████████▊| 357/363 [00:16<00:00, 24.24it/s]
                                                            
Job alexdaoud-trainer-famon-50949-v1-mkmlizer completed after 124.81s with status: succeeded
Stopping job with name alexdaoud-trainer-famon-50949-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.30s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexdaoud-trainer-famon-50949-v1
Waiting for inference service alexdaoud-trainer-famon-50949-v1 to be ready
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service alexdaoud-trainer-famon-50949-v1 ready after 271.2424440383911s
Pipeline stage MKMLDeployer completed in 271.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2933943271636963s
Received healthy response to inference request in 1.4572734832763672s
Received healthy response to inference request in 1.5379078388214111s
Received healthy response to inference request in 1.5603344440460205s
Received healthy response to inference request in 1.563093662261963s
5 requests
0 failed requests
5th percentile: 1.473400354385376
10th percentile: 1.4895272254943848
20th percentile: 1.5217809677124023
30th percentile: 1.542393159866333
40th percentile: 1.5513638019561768
50th percentile: 1.5603344440460205
60th percentile: 1.5614381313323975
70th percentile: 1.5625418186187745
80th percentile: 1.7091537952423097
90th percentile: 2.001274061203003
95th percentile: 2.1473341941833493
99th percentile: 2.2641823005676267
mean time: 1.6824007511138916
Pipeline stage StressChecker completed in 9.57s
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 0.76s
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 0.65s
Shutdown handler de-registered
alexdaoud-trainer-famon_50949_v1 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexdaoud-trainer-famon-50949-v1-profiler
Waiting for inference service alexdaoud-trainer-famon-50949-v1-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4074.36s
Shutdown handler de-registered
alexdaoud-trainer-famon_50949_v1 status is now inactive due to auto deactivation removed underperforming models
alexdaoud-trainer-famon_50949_v1 status is now torndown due to DeploymentManager action