chaiml-albert-dpo-0912-v_1751

submission_id: chaiml-albert-dpo-0912-v_1751_v1

developer_uid: chai_backend_admin

alignment_samples: 11442

alignment_score: 2.2690213023421224

best_of: 16

celo_rating: 1254.48

display_name: 0821v1-7

formatter: {'memory_template': 'Bot Name: {bot_name}\n####\n', 'prompt_template': '', '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': 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|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: True

language_model: ChaiML/albert_dpo_0912_virgo_edit_original

latencies: [{'batch_size': 1, 'throughput': 0.6348502174031848, 'latency_mean': 1.5750802278518676, 'latency_p50': 1.5797319412231445, 'latency_p90': 1.74267897605896}, {'batch_size': 2, 'throughput': 0.863439185274359, 'latency_mean': 2.3127452516555786, 'latency_p50': 2.324259400367737, 'latency_p90': 2.5800827503204347}, {'batch_size': 3, 'throughput': 0.9473054510720764, 'latency_mean': 3.1590849125385283, 'latency_p50': 3.181495428085327, 'latency_p90': 3.5967807531356812}, {'batch_size': 4, 'throughput': 0.9227206070070685, 'latency_mean': 4.3235387861728665, 'latency_p50': 4.376706957817078, 'latency_p90': 4.8298773765563965}, {'batch_size': 5, 'throughput': 0.8896456498813224, 'latency_mean': 5.594708054065705, 'latency_p50': 5.574099063873291, 'latency_p90': 6.355095458030701}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/albert_dpo_0912_v

model_name: 0821v1-7

model_num_parameters: 12772070400.0

model_repo: ChaiML/albert_dpo_0912_virgo_edit_original

model_size: 13B

num_battles: 11442

num_wins: 5857

propriety_score: 0.7533960292580982

propriety_total_count: 957.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 0.94

timestamp: 2024-09-13T19:01:46+00:00

us_pacific_date: 2024-09-13

win_ratio: 0.5118860339101555

Download Preference Data

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-albert-dpo-0912-v-1751-v1-mkmlizer
Waiting for job on chaiml-albert-dpo-0912-v-1751-v1-mkmlizer to finish
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║       /___/                                                         ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ║                                                                     ║
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: Downloaded to shared memory in 103.090s
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpes3e5io4, device:0
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: quantized model in 40.083s
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: Processed model ChaiML/albert_dpo_0912_virgo_edit_original in 143.173s
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v1
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v1/config.json
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v1/special_tokens_map.json
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v1/tokenizer_config.json
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v1/tokenizer.json
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-albert-dpo-0912-v-1751-v1/flywheel_model.0.safetensors
chaiml-albert-dpo-0912-v-1751-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:14, 24.06it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.88it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.70it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:10, 32.23it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:13, 24.63it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:15, 21.73it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:13, 24.38it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 28.88it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 26.46it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:10, 30.92it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:11, 27.49it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:09, 31.80it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.61it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 23.21it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.85it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 29.37it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 28.68it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:08, 31.06it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.23it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.12it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 29.39it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.76it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:12, 21.56it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:09, 26.85it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 24.97it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.58it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 29.92it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.60it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.14it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 30.25it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 26.65it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 25.39it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.77it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 28.95it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:07, 25.71it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.07it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 30.45it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 31.73it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 30.88it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.99it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 22.19it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 28.90it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 28.48it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.97it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.99it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.89it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.11it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 29.85it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.80it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.63it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.71it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 28.65it/s]
Loading 0:  66%|██████▌   | 239/363 [00:08<00:04, 26.17it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 32.67it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 30.39it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 32.72it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 31.40it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 25.76it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 23.09it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 29.99it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:03, 28.44it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.07it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.26it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.85it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 30.16it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 30.15it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 25.45it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.28it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.52it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.59it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 29.76it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 31.48it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 30.34it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 32.71it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 30.61it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  1.99it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.69it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.89it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.03it/s]
Loading 0: 100%|█████████▉| 362/363 [00:19<00:00,  7.16it/s]
                                                            
Job chaiml-albert-dpo-0912-v-1751-v1-mkmlizer completed after 166.83s with status: succeeded
Stopping job with name chaiml-albert-dpo-0912-v-1751-v1-mkmlizer
Pipeline stage MKMLizer completed in 169.16s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-albert-dpo-0912-v-1751-v1
Waiting for inference service chaiml-albert-dpo-0912-v-1751-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-albert-dpo-0912-v-1751-v1 ready after 180.8622214794159s
Pipeline stage MKMLDeployer completed in 181.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.880532741546631s
Received healthy response to inference request in 2.068460702896118s
Received healthy response to inference request in 1.734816074371338s
Received healthy response to inference request in 1.656388282775879s
Received healthy response to inference request in 2.460510015487671s
5 requests
0 failed requests
5th percentile: 1.6720738410949707
10th percentile: 1.6877593994140625
20th percentile: 1.719130516052246
30th percentile: 1.801545000076294
40th percentile: 1.935002851486206
50th percentile: 2.068460702896118
60th percentile: 2.225280427932739
70th percentile: 2.38210015296936
80th percentile: 2.544514560699463
90th percentile: 2.712523651123047
95th percentile: 2.796528196334839
99th percentile: 2.8637318325042727
mean time: 2.1601415634155274
Pipeline stage StressChecker completed in 11.36s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.18s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_1751_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 0.14s
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-albert-dpo-0912-v-1751-v1-profiler
Waiting for inference service chaiml-albert-dpo-0912-v-1751-v1-profiler to be ready
Inference service chaiml-albert-dpo-0912-v-1751-v1-profiler ready after 180.4229097366333s
Pipeline stage MKMLProfilerDeployer completed in 180.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-albert-dpo-09d4fac0889b488286d98a215f678b12d7-deplo5r7zc:/code/chaiverse_profiler_1726254701 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-albert-dpo-09d4fac0889b488286d98a215f678b12d7-deplo5r7zc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726254701 && python profiles.py profile --best_of_n 16 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 64 --summary /code/chaiverse_profiler_1726254701/summary.json'
kubectl exec -it chaiml-albert-dpo-09d4fac0889b488286d98a215f678b12d7-deplo5r7zc --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726254701/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1208.18s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-albert-dpo-0912-v-1751-v1-profiler is running
Tearing down inference service chaiml-albert-dpo-0912-v-1751-v1-profiler
Service chaiml-albert-dpo-0912-v-1751-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.72s
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_1751_v1 status is now inactive due to auto deactivation removed underperforming models