chaiml-espresso-ant-lla_1666

developer_uid: azuruce

submission_id: chaiml-espresso-ant-lla_1666_v12

model_name: chaiml-espresso-ant-lla_1666_v12

model_group: ChaiML/espresso_ant_llam

status: inactive

timestamp: 2024-12-05T08:54:09+00:00

num_battles: 9808

num_wins: 4924

celo_rating: 1264.2

family_friendly_score: 0.5838

family_friendly_standard_error: 0.006971048127792549

submission_type: basic

model_repo: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.39118120726124034, 'latency_mean': 2.556301779747009, 'latency_p50': 2.542745590209961, 'latency_p90': 2.817311334609985}, {'batch_size': 3, 'throughput': 0.8314235508840555, 'latency_mean': 3.6031555938720703, 'latency_p50': 3.613621711730957, 'latency_p90': 3.960176634788513}, {'batch_size': 5, 'throughput': 1.1051751352711152, 'latency_mean': 4.499929049015045, 'latency_p50': 4.530253529548645, 'latency_p90': 4.9758353471755985}, {'batch_size': 6, 'throughput': 1.1974196887886273, 'latency_mean': 4.983798965215683, 'latency_p50': 4.947353005409241, 'latency_p90': 5.667213058471679}, {'batch_size': 8, 'throughput': 1.3276435974026792, 'latency_mean': 5.989685819149018, 'latency_p50': 6.002651572227478, 'latency_p90': 6.620347952842712}, {'batch_size': 10, 'throughput': 1.405601312705642, 'latency_mean': 7.045453985929489, 'latency_p50': 7.022753119468689, 'latency_p90': 8.093346881866456}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-lla_1666_v12

is_internal_developer: True

language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.87

us_pacific_date: 2024-12-05

win_ratio: 0.5020391517128875

generation_params: {'temperature': 0.79, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, '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-espresso-ant-lla-1666-v12-mkmlizer
Waiting for job on chaiml-espresso-ant-lla-1666-v12-mkmlizer to finish
chaiml-espresso-ant-lla-1666-v12-mkmlizer: Downloaded to shared memory in 41.322s
chaiml-espresso-ant-lla-1666-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmpo2cl70, device:0
chaiml-espresso-ant-lla-1666-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-lla-1666-v12-mkmlizer: quantized model in 47.146s
chaiml-espresso-ant-lla-1666-v12-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha in 88.468s
chaiml-espresso-ant-lla-1666-v12-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-lla-1666-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-lla-1666-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v12
chaiml-espresso-ant-lla-1666-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v12/config.json
chaiml-espresso-ant-lla-1666-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v12/special_tokens_map.json
chaiml-espresso-ant-lla-1666-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v12/tokenizer_config.json
chaiml-espresso-ant-lla-1666-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v12/tokenizer.json
chaiml-espresso-ant-lla-1666-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v12/flywheel_model.1.safetensors
chaiml-espresso-ant-lla-1666-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v12/flywheel_model.0.safetensors
chaiml-espresso-ant-lla-1666-v12-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:22, 21.89it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:16, 29.64it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:18, 26.44it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:15, 32.18it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:16, 28.65it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:12, 36.74it/s]
Loading 0:   7%|▋         | 34/507 [00:01<00:13, 34.98it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:12, 37.48it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:12, 36.27it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:12, 35.62it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:13, 34.20it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:19, 22.88it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:19, 23.13it/s]
Loading 0:  12%|█▏        | 61/507 [00:02<00:18, 23.87it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:19, 22.78it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:16, 26.33it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:16, 26.45it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:14, 29.14it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:13, 31.83it/s]
Loading 0:  18%|█▊        | 89/507 [00:03<00:14, 28.42it/s]
Loading 0:  19%|█▊        | 94/507 [00:03<00:13, 31.30it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:15, 27.02it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:13, 30.70it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:14, 27.63it/s]
Loading 0:  22%|██▏       | 112/507 [00:03<00:12, 30.92it/s]
Loading 0:  23%|██▎       | 116/507 [00:04<00:20, 19.33it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:17, 22.24it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:14, 26.07it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:15, 24.64it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:13, 28.00it/s]
Loading 0:  28%|██▊       | 140/507 [00:05<00:13, 26.24it/s]
Loading 0:  29%|██▊       | 145/507 [00:05<00:11, 30.57it/s]
Loading 0:  29%|██▉       | 149/507 [00:05<00:12, 28.89it/s]
Loading 0:  31%|███       | 156/507 [00:05<00:09, 36.84it/s]
Loading 0:  32%|███▏      | 161/507 [00:05<00:09, 38.02it/s]
Loading 0:  33%|███▎      | 166/507 [00:05<00:08, 40.23it/s]
Loading 0:  34%|███▎      | 171/507 [00:06<00:14, 23.98it/s]
Loading 0:  35%|███▍      | 176/507 [00:06<00:13, 24.43it/s]
Loading 0:  36%|███▌      | 181/507 [00:06<00:11, 27.99it/s]
Loading 0:  36%|███▋      | 185/507 [00:06<00:12, 26.06it/s]
Loading 0:  37%|███▋      | 190/507 [00:06<00:10, 29.47it/s]
Loading 0:  38%|███▊      | 194/507 [00:06<00:11, 27.29it/s]
Loading 0:  39%|███▉      | 199/507 [00:06<00:09, 30.90it/s]
Loading 0:  40%|████      | 203/507 [00:07<00:10, 27.83it/s]
Loading 0:  41%|████      | 208/507 [00:07<00:09, 31.56it/s]
Loading 0:  42%|████▏     | 212/507 [00:07<00:10, 28.39it/s]
Loading 0:  43%|████▎     | 217/507 [00:07<00:08, 32.43it/s]
Loading 0:  44%|████▎     | 221/507 [00:07<00:09, 29.57it/s]
Loading 0:  44%|████▍     | 225/507 [00:08<00:13, 20.85it/s]
Loading 0:  45%|████▌     | 230/507 [00:08<00:12, 22.47it/s]
Loading 0:  46%|████▋     | 235/507 [00:08<00:10, 26.12it/s]
Loading 0:  47%|████▋     | 239/507 [00:08<00:10, 24.61it/s]
Loading 0:  48%|████▊     | 244/507 [00:08<00:09, 28.38it/s]
Loading 0:  49%|████▉     | 248/507 [00:08<00:10, 25.73it/s]
Loading 0:  50%|████▉     | 253/507 [00:08<00:08, 29.57it/s]
Loading 0:  51%|█████     | 257/507 [00:09<00:09, 27.29it/s]
Loading 0:  52%|█████▏    | 262/507 [00:09<00:07, 31.63it/s]
Loading 0:  52%|█████▏    | 266/507 [00:09<00:08, 28.97it/s]
Loading 0:  54%|█████▍    | 273/507 [00:09<00:06, 36.42it/s]
Loading 0:  55%|█████▍    | 277/507 [00:09<00:06, 34.74it/s]
Loading 0:  56%|█████▌    | 283/507 [00:09<00:06, 36.60it/s]
Loading 0:  57%|█████▋    | 287/507 [00:10<00:09, 24.04it/s]
Loading 0:  58%|█████▊    | 293/507 [00:10<00:08, 25.89it/s]
Loading 0:  59%|█████▉    | 298/507 [00:10<00:07, 28.99it/s]
Loading 0:  60%|█████▉    | 302/507 [00:26<03:25,  1.00s/it]
Loading 0:  61%|██████    | 307/507 [00:26<02:20,  1.42it/s]
Loading 0:  61%|██████▏   | 311/507 [00:26<01:45,  1.86it/s]
Loading 0:  63%|██████▎   | 318/507 [00:26<01:02,  3.01it/s]
Loading 0:  64%|██████▎   | 322/507 [00:26<00:47,  3.87it/s]
Loading 0:  64%|██████▍   | 327/507 [00:26<00:33,  5.33it/s]
Loading 0:  65%|██████▌   | 331/507 [00:27<00:25,  6.78it/s]
Loading 0:  66%|██████▌   | 335/507 [00:27<00:19,  8.70it/s]
Loading 0:  67%|██████▋   | 340/507 [00:27<00:15, 10.62it/s]
Loading 0:  68%|██████▊   | 344/507 [00:27<00:12, 12.90it/s]
Loading 0:  69%|██████▊   | 348/507 [00:27<00:10, 15.11it/s]
Loading 0:  70%|██████▉   | 354/507 [00:27<00:07, 20.71it/s]
Loading 0:  71%|███████   | 358/507 [00:27<00:06, 23.17it/s]
Loading 0:  72%|███████▏  | 363/507 [00:28<00:05, 26.99it/s]
Loading 0:  72%|███████▏  | 367/507 [00:28<00:05, 27.19it/s]
Loading 0:  73%|███████▎  | 372/507 [00:28<00:04, 30.24it/s]
Loading 0:  74%|███████▍  | 376/507 [00:28<00:04, 29.86it/s]
Loading 0:  75%|███████▍  | 380/507 [00:28<00:03, 31.80it/s]
Loading 0:  76%|███████▌  | 384/507 [00:28<00:04, 28.98it/s]
Loading 0:  77%|███████▋  | 389/507 [00:28<00:03, 32.41it/s]
Loading 0:  78%|███████▊  | 393/507 [00:28<00:03, 32.03it/s]
Loading 0:  78%|███████▊  | 397/507 [00:29<00:04, 23.61it/s]
Loading 0:  79%|███████▉  | 401/507 [00:29<00:04, 23.82it/s]
Loading 0:  80%|████████  | 408/507 [00:29<00:03, 30.64it/s]
Loading 0:  81%|████████▏ | 412/507 [00:29<00:03, 30.43it/s]
Loading 0:  82%|████████▏ | 417/507 [00:29<00:02, 33.01it/s]
Loading 0:  83%|████████▎ | 421/507 [00:29<00:02, 30.48it/s]
Loading 0:  84%|████████▍ | 425/507 [00:30<00:02, 32.00it/s]
Loading 0:  85%|████████▍ | 429/507 [00:30<00:02, 29.29it/s]
Loading 0:  85%|████████▌ | 433/507 [00:30<00:02, 31.31it/s]
Loading 0:  86%|████████▌ | 437/507 [00:30<00:02, 28.39it/s]
Loading 0:  88%|████████▊ | 444/507 [00:30<00:01, 35.43it/s]
Loading 0:  88%|████████▊ | 448/507 [00:30<00:01, 33.18it/s]
Loading 0:  89%|████████▉ | 452/507 [00:30<00:01, 34.41it/s]
Loading 0:  90%|████████▉ | 456/507 [00:33<00:09,  5.58it/s]
Loading 0:  91%|█████████ | 459/507 [00:33<00:07,  6.61it/s]
Loading 0:  92%|█████████▏| 465/507 [00:33<00:04,  9.59it/s]
Loading 0:  93%|█████████▎| 470/507 [00:33<00:02, 12.90it/s]
Loading 0:  93%|█████████▎| 474/507 [00:33<00:02, 14.58it/s]
Loading 0:  94%|█████████▍| 479/507 [00:33<00:01, 18.70it/s]
Loading 0:  95%|█████████▌| 483/507 [00:34<00:01, 19.94it/s]
Loading 0:  96%|█████████▋| 488/507 [00:34<00:00, 24.43it/s]
Loading 0:  97%|█████████▋| 492/507 [00:34<00:00, 23.91it/s]
Loading 0:  98%|█████████▊| 497/507 [00:34<00:00, 28.24it/s]
Loading 0:  99%|█████████▉| 501/507 [00:34<00:00, 26.47it/s]
Loading 0: 100%|█████████▉| 506/507 [00:34<00:00, 30.65it/s]
                                                            
Job chaiml-espresso-ant-lla-1666-v12-mkmlizer completed after 121.22s with status: succeeded
Stopping job with name chaiml-espresso-ant-lla-1666-v12-mkmlizer
Pipeline stage MKMLizer completed in 122.61s
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 chaiml-espresso-ant-lla-1666-v12
Waiting for inference service chaiml-espresso-ant-lla-1666-v12 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
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 chaiml-espresso-ant-llam_1666_v9: ('http://chaiml-espresso-ant-llam-1666-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:55610->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-espresso-ant-lla-1666-v12 ready after 165.80980491638184s
Pipeline stage MKMLDeployer completed in 167.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.898393392562866s
Received healthy response to inference request in 2.3819644451141357s
Received healthy response to inference request in 2.2277371883392334s
Received healthy response to inference request in 2.3417587280273438s
Received healthy response to inference request in 2.264878034591675s
5 requests
0 failed requests
5th percentile: 2.2351653575897217
10th percentile: 2.24259352684021
20th percentile: 2.2574498653411865
30th percentile: 2.2802541732788084
40th percentile: 2.311006450653076
50th percentile: 2.3417587280273438
60th percentile: 2.3578410148620605
70th percentile: 2.3739233016967773
80th percentile: 2.485250234603882
90th percentile: 2.691821813583374
95th percentile: 2.79510760307312
99th percentile: 2.877736234664917
mean time: 2.4229463577270507
Pipeline stage StressChecker completed in 13.35s
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 2.08s
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 1.97s
Shutdown handler de-registered
chaiml-espresso-ant-lla_1666_v12 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 3083.37s
Shutdown handler de-registered
chaiml-espresso-ant-lla_1666_v12 status is now inactive due to auto deactivation removed underperforming models