hastagaras-snl-ft-model-4

submission_id: hastagaras-snl-ft-model-4_v1

developer_uid: Hastagaras

best_of: 8

celo_rating: 1241.37

display_name: hastagaras-snl-ft-model-4_v1

family_friendly_score: 0.5738

family_friendly_standard_error: 0.006993619377689924

formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n\n', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: False

language_model: Hastagaras/snl-ft-model-4

latencies: [{'batch_size': 1, 'throughput': 0.8488515733520146, 'latency_mean': 1.1779921340942383, 'latency_p50': 1.1878149509429932, 'latency_p90': 1.298702025413513}, {'batch_size': 4, 'throughput': 1.7765328472892965, 'latency_mean': 2.2398795449733733, 'latency_p50': 2.2434102296829224, 'latency_p90': 2.4842559337615966}, {'batch_size': 5, 'throughput': 1.9351469809006854, 'latency_mean': 2.569787504673004, 'latency_p50': 2.56773042678833, 'latency_p90': 2.853538346290588}, {'batch_size': 8, 'throughput': 2.119688340968447, 'latency_mean': 3.7427669298648834, 'latency_p50': 3.7303181886672974, 'latency_p90': 4.154277062416076}, {'batch_size': 10, 'throughput': 2.1750315494136694, 'latency_mean': 4.565949482917786, 'latency_p50': 4.612348437309265, 'latency_p90': 5.116627883911133}, {'batch_size': 12, 'throughput': 2.2268068076089147, 'latency_mean': 5.331234111785888, 'latency_p50': 5.295519828796387, 'latency_p90': 6.171623587608337}, {'batch_size': 15, 'throughput': 2.218290380946914, 'latency_mean': 6.676664378643036, 'latency_p50': 6.734653115272522, 'latency_p90': 7.480186033248901}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Hastagaras/snl-ft-model-

model_name: hastagaras-snl-ft-model-4_v1

model_num_parameters: 8030261248.0

model_repo: Hastagaras/snl-ft-model-4

model_size: 8B

num_battles: 20240

num_wins: 10117

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 2.13

timestamp: 2024-11-07T16:41:46+00:00

us_pacific_date: 2024-11-07

win_ratio: 0.49985177865612646

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 hastagaras-snl-ft-model-4-v1-mkmlizer
Waiting for job on hastagaras-snl-ft-model-4-v1-mkmlizer to finish
hastagaras-snl-ft-model-4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-snl-ft-model-4-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║                                                                     ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║  Version: 0.11.33                                                   ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║                                                                     ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║                                                                     ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ║                                                                     ║
hastagaras-snl-ft-model-4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-snl-ft-model-4-v1-mkmlizer: Downloaded to shared memory in 35.670s
hastagaras-snl-ft-model-4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4mr6zg2z, device:0
hastagaras-snl-ft-model-4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
hastagaras-snl-ft-model-4-v1-mkmlizer: quantized model in 27.171s
hastagaras-snl-ft-model-4-v1-mkmlizer: Processed model Hastagaras/snl-ft-model-4 in 62.841s
hastagaras-snl-ft-model-4-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-snl-ft-model-4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-snl-ft-model-4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-snl-ft-model-4-v1
hastagaras-snl-ft-model-4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-snl-ft-model-4-v1/config.json
hastagaras-snl-ft-model-4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-snl-ft-model-4-v1/special_tokens_map.json
hastagaras-snl-ft-model-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-snl-ft-model-4-v1/tokenizer_config.json
hastagaras-snl-ft-model-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-snl-ft-model-4-v1/tokenizer.json
hastagaras-snl-ft-model-4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-snl-ft-model-4-v1/flywheel_model.0.safetensors
hastagaras-snl-ft-model-4-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 29.31it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 50.71it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:06, 44.12it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 41.73it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 47.40it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 45.36it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 43.77it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:05, 47.46it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:05, 46.98it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:05, 43.29it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 47.10it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 54.44it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:04, 51.48it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:05, 34.90it/s]
Loading 0:  33%|███▎      | 95/291 [00:02<00:05, 35.86it/s]
Loading 0:  35%|███▌      | 102/291 [00:02<00:04, 41.60it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:04, 44.89it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:04, 39.11it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 45.47it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 44.29it/s]
Loading 0:  45%|████▌     | 132/291 [00:03<00:03, 42.30it/s]
Loading 0:  47%|████▋     | 138/291 [00:03<00:03, 44.61it/s]
Loading 0:  49%|████▉     | 143/291 [00:03<00:03, 44.09it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 45.22it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:03, 43.58it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:03, 43.76it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 49.09it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 46.63it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 50.83it/s]
Loading 0:  64%|██████▎   | 185/291 [00:04<00:02, 52.13it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 30.71it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 31.70it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 33.97it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 35.41it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:02, 36.73it/s]
Loading 0:  74%|███████▍  | 216/291 [00:05<00:01, 38.96it/s]
Loading 0:  76%|███████▌  | 221/291 [00:05<00:02, 33.24it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 40.09it/s]
Loading 0:  80%|████████  | 233/291 [00:05<00:01, 40.74it/s]
Loading 0:  82%|████████▏ | 239/291 [00:05<00:01, 38.99it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 47.70it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 45.99it/s]
Loading 0:  89%|████████▊ | 258/291 [00:06<00:00, 44.37it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 50.03it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 47.54it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 47.26it/s]
Loading 0:  97%|█████████▋| 281/291 [00:06<00:00, 46.23it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 39.23it/s]
Loading 0: 100%|██████████| 291/291 [00:12<00:00,  3.06it/s]
                                                            
Job hastagaras-snl-ft-model-4-v1-mkmlizer completed after 84.42s with status: succeeded
Stopping job with name hastagaras-snl-ft-model-4-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.00s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service hastagaras-snl-ft-model-4-v1
Waiting for inference service hastagaras-snl-ft-model-4-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service hastagaras-snl-ft-model-4-v1 ready after 170.63248586654663s
Pipeline stage MKMLDeployer completed in 171.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.300250768661499s
Received healthy response to inference request in 1.524428367614746s
Received healthy response to inference request in 1.302779197692871s
Received healthy response to inference request in 1.1723556518554688s
Received healthy response to inference request in 1.189223051071167s
5 requests
0 failed requests
5th percentile: 1.1757291316986085
10th percentile: 1.179102611541748
20th percentile: 1.1858495712280273
30th percentile: 1.2119342803955078
40th percentile: 1.2573567390441895
50th percentile: 1.302779197692871
60th percentile: 1.391438865661621
70th percentile: 1.4800985336303711
80th percentile: 1.679592847824097
90th percentile: 1.9899218082427979
95th percentile: 2.1450862884521484
99th percentile: 2.269217872619629
mean time: 1.4978074073791503
Pipeline stage StressChecker completed in 9.19s
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 2.84s
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 2.88s
Shutdown handler de-registered
hastagaras-snl-ft-model-4_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service hastagaras-snl-ft-model-4-v1-profiler
Waiting for inference service hastagaras-snl-ft-model-4-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2394.41s
Shutdown handler de-registered
hastagaras-snl-ft-model-4_v1 status is now inactive due to auto deactivation removed underperforming models