chaiml-small-story-607-e_8056

developer_uid: azuruce

submission_id: chaiml-small-story-607-e_8056_v3

model_name: temp1p1

model_group: ChaiML/small_story_607-e

status: inactive

timestamp: 2024-11-27T20:54:26+00:00

num_battles: 13139

num_wins: 6364

celo_rating: 1251.45

family_friendly_score: 0.5798

family_friendly_standard_error: 0.006980429213164474

submission_type: basic

model_repo: ChaiML/small_story_607-ed10-100_true_rpg_v3_sft

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3854361591481706, 'latency_mean': 2.594378727674484, 'latency_p50': 2.5889488458633423, 'latency_p90': 2.8572251558303834}, {'batch_size': 3, 'throughput': 0.8142089982315872, 'latency_mean': 3.6726471507549285, 'latency_p50': 3.6835999488830566, 'latency_p90': 3.9613825559616087}, {'batch_size': 5, 'throughput': 1.0881018251685037, 'latency_mean': 4.570838874578476, 'latency_p50': 4.561459064483643, 'latency_p90': 5.206425523757934}, {'batch_size': 6, 'throughput': 1.1755767428079913, 'latency_mean': 5.069408477544784, 'latency_p50': 5.0740824937820435, 'latency_p90': 5.686477732658386}, {'batch_size': 10, 'throughput': 1.3886421460468379, 'latency_mean': 7.115333062410355, 'latency_p50': 7.12811815738678, 'latency_p90': 8.077386403083802}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: temp1p1

is_internal_developer: True

language_model: ChaiML/small_story_607-ed10-100_true_rpg_v3_sft

model_size: 22B

ranking_group: single

throughput_3p7s: 0.83

us_pacific_date: 2024-11-27

win_ratio: 0.4843595402998706

generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, '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-small-story-607-e-8056-v3-mkmlizer
Waiting for job on chaiml-small-story-607-e-8056-v3-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-story-607-e-8056-v3-mkmlizer: Downloaded to shared memory in 56.897s
chaiml-small-story-607-e-8056-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpetkkl1n2, device:0
chaiml-small-story-607-e-8056-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission function_pifab_2024-11-27: max() arg is an empty sequence
chaiml-small-story-607-e-8056-v3-mkmlizer: quantized model in 53.712s
chaiml-small-story-607-e-8056-v3-mkmlizer: Processed model ChaiML/small_story_607-ed10-100_true_rpg_v3_sft in 110.609s
chaiml-small-story-607-e-8056-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-story-607-e-8056-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-story-607-e-8056-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-story-607-e-8056-v3
chaiml-small-story-607-e-8056-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-story-607-e-8056-v3/config.json
chaiml-small-story-607-e-8056-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-story-607-e-8056-v3/special_tokens_map.json
chaiml-small-story-607-e-8056-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-story-607-e-8056-v3/flywheel_model.1.safetensors
chaiml-small-story-607-e-8056-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-story-607-e-8056-v3/flywheel_model.0.safetensors
chaiml-small-story-607-e-8056-v3-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:23, 21.14it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:16, 30.75it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:17, 27.60it/s]
Loading 0:   4%|▍         | 21/507 [00:00<00:12, 37.64it/s]
Loading 0:   5%|▌         | 26/507 [00:00<00:12, 37.09it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:12, 37.27it/s]
Loading 0:   7%|▋         | 34/507 [00:00<00:13, 35.92it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:11, 39.07it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 39.42it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:13, 34.69it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:19, 23.75it/s]
Loading 0:  11%|█         | 56/507 [00:01<00:20, 22.25it/s]
Loading 0:  12%|█▏        | 63/507 [00:02<00:15, 29.50it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:14, 29.80it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:13, 33.13it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:12, 34.36it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 38.73it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 38.69it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 38.97it/s]
Loading 0:  20%|█▉        | 101/507 [00:02<00:10, 38.59it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:10, 38.78it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:10, 36.51it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:15, 25.88it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:15, 24.94it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 25.94it/s]
Loading 0:  25%|██▌       | 127/507 [00:03<00:12, 30.46it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:13, 28.12it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:11, 32.30it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:12, 29.81it/s]
Loading 0:  29%|██▊       | 145/507 [00:04<00:10, 34.09it/s]
Loading 0:  29%|██▉       | 149/507 [00:04<00:11, 30.71it/s]
Loading 0:  30%|███       | 154/507 [00:04<00:10, 34.52it/s]
Loading 0:  31%|███       | 158/507 [00:04<00:11, 30.88it/s]
Loading 0:  32%|███▏      | 164/507 [00:05<00:09, 35.20it/s]
Loading 0:  33%|███▎      | 168/507 [00:05<00:09, 35.91it/s]
Loading 0:  34%|███▍      | 172/507 [00:05<00:13, 24.09it/s]
Loading 0:  35%|███▍      | 176/507 [00:05<00:13, 24.04it/s]
Loading 0:  36%|███▌      | 181/507 [00:05<00:11, 28.78it/s]
Loading 0:  36%|███▋      | 185/507 [00:05<00:11, 27.85it/s]
Loading 0:  37%|███▋      | 190/507 [00:06<00:09, 32.33it/s]
Loading 0:  38%|███▊      | 194/507 [00:06<00:10, 29.24it/s]
Loading 0:  39%|███▉      | 199/507 [00:06<00:09, 32.95it/s]
Loading 0:  40%|████      | 203/507 [00:06<00:10, 30.08it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 37.56it/s]
Loading 0:  42%|████▏     | 215/507 [00:06<00:07, 36.87it/s]
Loading 0:  43%|████▎     | 219/507 [00:06<00:09, 29.57it/s]
Loading 0:  44%|████▍     | 223/507 [00:07<00:08, 31.70it/s]
Loading 0:  45%|████▍     | 227/507 [00:07<00:10, 27.52it/s]
Loading 0:  46%|████▌     | 231/507 [00:07<00:10, 26.53it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:08, 31.31it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 30.43it/s]
Loading 0:  48%|████▊     | 245/507 [00:07<00:08, 31.97it/s]
Loading 0:  49%|████▉     | 249/507 [00:07<00:08, 28.75it/s]
Loading 0:  50%|████▉     | 253/507 [00:08<00:08, 30.92it/s]
Loading 0:  51%|█████     | 257/507 [00:08<00:09, 27.68it/s]
Loading 0:  52%|█████▏    | 262/507 [00:08<00:07, 32.09it/s]
Loading 0:  52%|█████▏    | 266/507 [00:08<00:08, 28.66it/s]
Loading 0:  53%|█████▎    | 271/507 [00:08<00:07, 33.04it/s]
Loading 0:  54%|█████▍    | 275/507 [00:08<00:07, 30.10it/s]
Loading 0:  55%|█████▌    | 280/507 [00:08<00:06, 33.88it/s]
Loading 0:  56%|█████▌    | 284/507 [00:09<00:08, 25.43it/s]
Loading 0:  57%|█████▋    | 288/507 [00:09<00:08, 24.99it/s]
Loading 0:  58%|█████▊    | 293/507 [00:09<00:08, 25.60it/s]
Loading 0:  59%|█████▉    | 298/507 [00:09<00:07, 29.70it/s]
Loading 0:  59%|█████▉    | 299/507 [00:20<00:07, 29.70it/s]
Loading 0:  59%|█████▉    | 300/507 [00:28<05:17,  1.53s/it]
Loading 0:  60%|█████▉    | 302/507 [00:29<04:20,  1.27s/it]
Loading 0:  61%|██████    | 307/507 [00:29<02:36,  1.28it/s]
Loading 0:  61%|██████    | 310/507 [00:29<01:57,  1.68it/s]
Loading 0:  62%|██████▏   | 313/507 [00:29<01:26,  2.23it/s]
Loading 0:  63%|██████▎   | 318/507 [00:29<00:53,  3.53it/s]
Loading 0:  64%|██████▎   | 322/507 [00:29<00:37,  4.87it/s]
Loading 0:  64%|██████▍   | 327/507 [00:29<00:25,  7.13it/s]
Loading 0:  65%|██████▌   | 331/507 [00:29<00:19,  9.21it/s]
Loading 0:  66%|██████▌   | 335/507 [00:30<00:14, 11.73it/s]
Loading 0:  67%|██████▋   | 340/507 [00:30<00:12, 13.52it/s]
Loading 0:  68%|██████▊   | 344/507 [00:30<00:10, 16.06it/s]
Loading 0:  69%|██████▊   | 348/507 [00:30<00:08, 17.89it/s]
Loading 0:  70%|██████▉   | 354/507 [00:30<00:06, 23.63it/s]
Loading 0:  71%|███████   | 358/507 [00:30<00:05, 25.67it/s]
Loading 0:  72%|███████▏  | 363/507 [00:30<00:04, 30.13it/s]
Loading 0:  72%|███████▏  | 367/507 [00:31<00:04, 30.68it/s]
Loading 0:  73%|███████▎  | 372/507 [00:31<00:03, 34.66it/s]
Loading 0:  74%|███████▍  | 376/507 [00:31<00:03, 35.17it/s]
Loading 0:  75%|███████▌  | 382/507 [00:31<00:03, 38.73it/s]
Loading 0:  76%|███████▋  | 387/507 [00:31<00:02, 41.49it/s]
Loading 0:  77%|███████▋  | 392/507 [00:31<00:03, 36.30it/s]
Loading 0:  78%|███████▊  | 396/507 [00:31<00:03, 28.04it/s]
Loading 0:  79%|███████▉  | 401/507 [00:32<00:03, 29.18it/s]
Loading 0:  80%|████████  | 408/507 [00:32<00:02, 35.88it/s]
Loading 0:  81%|████████▏ | 412/507 [00:32<00:02, 35.25it/s]
Loading 0:  82%|████████▏ | 417/507 [00:32<00:02, 37.54it/s]
Loading 0:  83%|████████▎ | 421/507 [00:32<00:02, 36.50it/s]
Loading 0:  84%|████████▍ | 426/507 [00:32<00:02, 39.67it/s]
Loading 0:  85%|████████▌ | 431/507 [00:32<00:02, 36.72it/s]
Loading 0:  86%|████████▌ | 435/507 [00:32<00:01, 36.74it/s]
Loading 0:  87%|████████▋ | 439/507 [00:33<00:01, 36.36it/s]
Loading 0:  88%|████████▊ | 445/507 [00:33<00:01, 39.69it/s]
Loading 0:  89%|████████▉ | 451/507 [00:33<00:01, 39.72it/s]
Loading 0:  90%|████████▉ | 456/507 [00:35<00:07,  6.57it/s]
Loading 0:  91%|█████████ | 459/507 [00:35<00:06,  7.52it/s]
Loading 0:  92%|█████████▏| 465/507 [00:36<00:03, 10.57it/s]
Loading 0:  93%|█████████▎| 472/507 [00:36<00:02, 15.24it/s]
Loading 0:  94%|█████████▍| 476/507 [00:36<00:01, 17.12it/s]
Loading 0:  95%|█████████▍| 481/507 [00:36<00:01, 20.50it/s]
Loading 0:  96%|█████████▌| 485/507 [00:36<00:00, 22.07it/s]
Loading 0:  97%|█████████▋| 490/507 [00:36<00:00, 25.34it/s]
Loading 0:  97%|█████████▋| 494/507 [00:36<00:00, 26.19it/s]
Loading 0:  98%|█████████▊| 499/507 [00:36<00:00, 29.10it/s]
Loading 0:  99%|█████████▉| 503/507 [00:37<00:00, 29.20it/s]
                                                            
Job chaiml-small-story-607-e-8056-v3-mkmlizer completed after 144.52s with status: succeeded
Stopping job with name chaiml-small-story-607-e-8056-v3-mkmlizer
Pipeline stage MKMLizer completed in 145.03s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-small-story-607-e-8056-v3
Waiting for inference service chaiml-small-story-607-e-8056-v3 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission function_pifab_2024-11-27: max() arg is an empty sequence
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
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
Failed to get response for submission function_pifab_2024-11-27: max() arg is an empty sequence
Inference service chaiml-small-story-607-e-8056-v3 ready after 130.68237853050232s
Pipeline stage MKMLDeployer completed in 131.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8967742919921875s
Received healthy response to inference request in 2.2562472820281982s
Received healthy response to inference request in 2.605280637741089s
Received healthy response to inference request in 2.358130693435669s
Received healthy response to inference request in 2.421231746673584s
5 requests
0 failed requests
5th percentile: 2.2766239643096924
10th percentile: 2.2970006465911865
20th percentile: 2.337754011154175
30th percentile: 2.370750904083252
40th percentile: 2.395991325378418
50th percentile: 2.421231746673584
60th percentile: 2.494851303100586
70th percentile: 2.568470859527588
80th percentile: 2.6635793685913085
90th percentile: 2.7801768302917482
95th percentile: 2.838475561141968
99th percentile: 2.8851145458221437
mean time: 2.5075329303741456
Pipeline stage StressChecker completed in 14.09s
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 2.51s
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 2.38s
Shutdown handler de-registered
chaiml-small-story-607-e_8056_v3 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-small-story-607-e-8056-v3-profiler
Waiting for inference service chaiml-small-story-607-e-8056-v3-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 3475.55s
Shutdown handler de-registered
chaiml-small-story-607-e_8056_v3 status is now inactive due to auto deactivation removed underperforming models