chaiml-ezstorytellingsft-1

submission_id: chaiml-ezstorytellingsft-1_v1

developer_uid: chai_backend_admin

best_of: 8

celo_rating: 1259.77

display_name: chaiml-ezstorytellingsft-1_v1

family_friendly_score: 0.5748

family_friendly_standard_error: 0.006991494260885866

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}

generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A6000': 1}

is_internal_developer: True

language_model: ChaiML/EZStorytellingSFT-1

latencies: [{'batch_size': 1, 'throughput': 0.37667694909278754, 'latency_mean': 2.6547095239162446, 'latency_p50': 2.6614365577697754, 'latency_p90': 2.945593166351318}, {'batch_size': 2, 'throughput': 0.598458226656475, 'latency_mean': 3.3391694056987764, 'latency_p50': 3.3240623474121094, 'latency_p90': 3.6667348384857177}, {'batch_size': 3, 'throughput': 0.7644924875629696, 'latency_mean': 3.911533155441284, 'latency_p50': 3.881407380104065, 'latency_p90': 4.356096291542054}, {'batch_size': 4, 'throughput': 0.8806624285112042, 'latency_mean': 4.519917235374451, 'latency_p50': 4.505727648735046, 'latency_p90': 5.107357287406922}, {'batch_size': 5, 'throughput': 0.9638438531428764, 'latency_mean': 5.166256476640701, 'latency_p50': 5.190949201583862, 'latency_p90': 5.7300729036331175}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/EZStorytellingSFT

model_name: chaiml-ezstorytellingsft-1_v1

model_num_parameters: 22247282688.0

model_repo: ChaiML/EZStorytellingSFT-1

model_size: 22B

num_battles: 11935

num_wins: 6134

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 0.71

timestamp: 2024-11-19T07:20:58+00:00

us_pacific_date: 2024-11-18

win_ratio: 0.5139505655634687

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-ezstorytellingsft-1-v1-mkmlizer
Waiting for job on chaiml-ezstorytellingsft-1-v1-mkmlizer to finish
chaiml-ezstorytellingsft-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║       /___/                                                         ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ezstorytellingsft-1-v1-mkmlizer: Downloaded to shared memory in 81.177s
chaiml-ezstorytellingsft-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr252o_jg, device:0
chaiml-ezstorytellingsft-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_gerot_2024-10-19: ('http://sao10k-mn-12b-lyra-v4a1-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:52418->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-ezstorytellingsft-1-v1-mkmlizer: quantized model in 42.964s
chaiml-ezstorytellingsft-1-v1-mkmlizer: Processed model ChaiML/EZStorytellingSFT-1 in 124.141s
chaiml-ezstorytellingsft-1-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ezstorytellingsft-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ezstorytellingsft-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ezstorytellingsft-1-v1
chaiml-ezstorytellingsft-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-1-v1/config.json
chaiml-ezstorytellingsft-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-1-v1/special_tokens_map.json
chaiml-ezstorytellingsft-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-1-v1/tokenizer_config.json
chaiml-ezstorytellingsft-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-1-v1/tokenizer.json
chaiml-ezstorytellingsft-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingsft-1-v1/flywheel_model.1.safetensors
chaiml-ezstorytellingsft-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingsft-1-v1/flywheel_model.0.safetensors
chaiml-ezstorytellingsft-1-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 24.05it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 40.97it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 40.30it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:11, 41.01it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 42.67it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 34.73it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:11, 41.34it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 40.45it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:13, 34.99it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:17, 26.47it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:17, 26.19it/s]
Loading 0:  12%|█▏        | 61/507 [00:01<00:15, 28.60it/s]
Loading 0:  13%|█▎        | 65/507 [00:01<00:16, 27.29it/s]
Loading 0:  14%|█▍        | 72/507 [00:02<00:12, 35.91it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:10, 40.58it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:10, 39.22it/s]
Loading 0:  17%|█▋        | 88/507 [00:02<00:10, 39.01it/s]
Loading 0:  18%|█▊        | 93/507 [00:02<00:10, 40.29it/s]
Loading 0:  19%|█▉        | 98/507 [00:02<00:11, 34.16it/s]
Loading 0:  21%|██        | 105/507 [00:02<00:09, 40.38it/s]
Loading 0:  22%|██▏       | 110/507 [00:03<00:10, 37.97it/s]
Loading 0:  23%|██▎       | 115/507 [00:03<00:14, 27.71it/s]
Loading 0:  23%|██▎       | 119/507 [00:03<00:13, 29.18it/s]
Loading 0:  24%|██▍       | 123/507 [00:03<00:13, 27.89it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:11, 32.75it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:11, 33.02it/s]
Loading 0:  27%|██▋       | 138/507 [00:03<00:10, 36.50it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 35.65it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 38.76it/s]
Loading 0:  30%|██▉       | 152/507 [00:04<00:09, 37.33it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 36.82it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 35.18it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 36.29it/s]
Loading 0:  33%|███▎      | 169/507 [00:04<00:11, 28.94it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 30.04it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 29.67it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 35.88it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 35.49it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 38.42it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:08, 35.82it/s]
Loading 0:  40%|███▉      | 201/507 [00:05<00:08, 36.95it/s]
Loading 0:  40%|████      | 205/507 [00:05<00:08, 34.73it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:08, 36.30it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:08, 34.13it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:08, 33.86it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:08, 34.10it/s]
Loading 0:  45%|████▍     | 226/507 [00:06<00:10, 25.65it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:10, 25.92it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:08, 33.49it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 33.03it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 36.03it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 36.01it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 38.79it/s]
Loading 0:  51%|█████▏    | 260/507 [00:07<00:06, 39.16it/s]
Loading 0:  52%|█████▏    | 265/507 [00:07<00:06, 38.83it/s]
Loading 0:  53%|█████▎    | 269/507 [00:07<00:06, 36.87it/s]
Loading 0:  54%|█████▍    | 274/507 [00:07<00:06, 38.21it/s]
Loading 0:  55%|█████▌    | 279/507 [00:08<00:05, 40.44it/s]
Loading 0:  56%|█████▌    | 284/507 [00:08<00:07, 29.04it/s]
Loading 0:  57%|█████▋    | 288/507 [00:08<00:07, 28.28it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 29.10it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 29.10it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:50,  1.22it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:27,  1.39it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:38,  2.03it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:17,  2.53it/s]
Loading 0:  62%|██████▏   | 313/507 [00:23<01:00,  3.23it/s]
Loading 0:  63%|██████▎   | 318/507 [00:23<00:38,  4.86it/s]
Loading 0:  64%|██████▎   | 322/507 [00:23<00:28,  6.49it/s]
Loading 0:  65%|██████▍   | 328/507 [00:23<00:18,  9.74it/s]
Loading 0:  66%|██████▌   | 333/507 [00:24<00:13, 12.98it/s]
Loading 0:  67%|██████▋   | 338/507 [00:24<00:10, 16.81it/s]
Loading 0:  68%|██████▊   | 343/507 [00:24<00:10, 16.10it/s]
Loading 0:  68%|██████▊   | 347/507 [00:24<00:08, 18.05it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:06, 25.25it/s]
Loading 0:  71%|███████   | 359/507 [00:24<00:05, 28.29it/s]
Loading 0:  72%|███████▏  | 364/507 [00:24<00:04, 31.48it/s]
Loading 0:  73%|███████▎  | 369/507 [00:25<00:03, 34.76it/s]
Loading 0:  74%|███████▍  | 374/507 [00:25<00:04, 32.53it/s]
Loading 0:  75%|███████▌  | 382/507 [00:25<00:03, 40.36it/s]
Loading 0:  76%|███████▋  | 387/507 [00:25<00:02, 41.01it/s]
Loading 0:  77%|███████▋  | 392/507 [00:25<00:03, 36.93it/s]
Loading 0:  78%|███████▊  | 397/507 [00:25<00:03, 29.78it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 29.03it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 35.70it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 35.31it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 38.24it/s]
Loading 0:  83%|████████▎ | 422/507 [00:26<00:02, 38.66it/s]
Loading 0:  84%|████████▍ | 427/507 [00:26<00:02, 39.78it/s]
Loading 0:  85%|████████▌ | 432/507 [00:26<00:01, 41.65it/s]
Loading 0:  86%|████████▌ | 437/507 [00:26<00:01, 35.20it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 40.71it/s]
Loading 0:  89%|████████▊ | 449/507 [00:27<00:01, 38.48it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 35.11it/s]
Loading 0:  90%|█████████ | 458/507 [00:29<00:07,  6.33it/s]
Loading 0:  91%|█████████ | 461/507 [00:29<00:06,  7.49it/s]
Loading 0:  92%|█████████▏| 465/507 [00:29<00:04,  9.46it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.50it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 16.79it/s]
Loading 0:  95%|█████████▍| 480/507 [00:30<00:01, 19.82it/s]
Loading 0:  95%|█████████▌| 484/507 [00:30<00:01, 21.43it/s]
Loading 0:  97%|█████████▋| 490/507 [00:30<00:00, 27.43it/s]
Loading 0:  97%|█████████▋| 494/507 [00:30<00:00, 28.45it/s]
Loading 0:  98%|█████████▊| 499/507 [00:30<00:00, 31.39it/s]
Loading 0:  99%|█████████▉| 503/507 [00:30<00:00, 31.67it/s]
                                                            
Job chaiml-ezstorytellingsft-1-v1-mkmlizer completed after 145.98s with status: succeeded
Stopping job with name chaiml-ezstorytellingsft-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.54s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ezstorytellingsft-1-v1
Waiting for inference service chaiml-ezstorytellingsft-1-v1 to be ready
Inference service chaiml-ezstorytellingsft-1-v1 ready after 190.9804995059967s
Pipeline stage MKMLDeployer completed in 191.57s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.7283952236175537s
Received healthy response to inference request in 2.839433193206787s
Received healthy response to inference request in 2.817153215408325s
Received healthy response to inference request in 3.226012706756592s
Received healthy response to inference request in 3.061530351638794s
5 requests
0 failed requests
5th percentile: 2.8216092109680178
10th percentile: 2.82606520652771
20th percentile: 2.8349771976470945
30th percentile: 2.8838526248931884
40th percentile: 2.9726914882659914
50th percentile: 3.061530351638794
60th percentile: 3.127323293685913
70th percentile: 3.193116235733032
80th percentile: 3.326489210128784
90th percentile: 3.527442216873169
95th percentile: 3.6279187202453613
99th percentile: 3.708299922943115
mean time: 3.1345049381256103
Pipeline stage StressChecker completed in 17.10s
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 2.33s
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 2.13s
Shutdown handler de-registered
chaiml-ezstorytellingsft-1_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3350.74s
Shutdown handler de-registered
chaiml-ezstorytellingsft-1_v1 status is now inactive due to auto deactivation removed underperforming models