chaiml-dpo-training-alb_26034

developer_uid: azuruce

submission_id: chaiml-dpo-training-alb_26034_v2

model_name: chaiml-dpo-training-alb_26034_v2

model_group: ChaiML/dpo-training-albe

status: torndown

timestamp: 2025-01-06T17:21:30+00:00

num_battles: 15923

num_wins: 8005

celo_rating: 1265.44

family_friendly_score: 0.598

family_friendly_standard_error: 0.0069339166421294686

submission_type: basic

model_repo: ChaiML/dpo-training-albert-4n8g

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6368302618147944, 'latency_mean': 1.5701835393905639, 'latency_p50': 1.5686558485031128, 'latency_p90': 1.7321069240570068}, {'batch_size': 3, 'throughput': 1.2704612872484864, 'latency_mean': 2.3468940794467925, 'latency_p50': 2.368001699447632, 'latency_p90': 2.5567114114761353}, {'batch_size': 5, 'throughput': 1.6084463805623075, 'latency_mean': 3.0927650463581084, 'latency_p50': 3.102829933166504, 'latency_p90': 3.537783074378967}, {'batch_size': 6, 'throughput': 1.73294251687488, 'latency_mean': 3.4430963659286498, 'latency_p50': 3.4460699558258057, 'latency_p90': 3.8581096172332763}, {'batch_size': 8, 'throughput': 1.8731277225818272, 'latency_mean': 4.24343204498291, 'latency_p50': 4.26966118812561, 'latency_p90': 4.710419511795044}, {'batch_size': 10, 'throughput': 1.967522899826988, 'latency_mean': 5.050047534704208, 'latency_p50': 5.050065398216248, 'latency_p90': 5.744907355308532}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-dpo-training-alb_26034_v2

is_internal_developer: False

language_model: ChaiML/dpo-training-albert-4n8g

model_size: 13B

ranking_group: single

throughput_3p7s: 1.8

us_pacific_date: 2025-01-06

win_ratio: 0.5027318972555423

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['User:', 'Bot:', '####', '<|eot_id|>', '\n', 'You:', '</s>', 'Me', '<|im_end|>'], '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-dpo-training-alb-26034-v2-mkmlizer
Waiting for job on chaiml-dpo-training-alb-26034-v2-mkmlizer to finish
chaiml-dpo-training-alb-26034-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║       /___/                                                         ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║                                                                     ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║                                                                     ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║                                                                     ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ║                                                                     ║
chaiml-dpo-training-alb-26034-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-dpo-training-alb-26034-v2-mkmlizer: Downloaded to shared memory in 33.085s
chaiml-dpo-training-alb-26034-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsuppr15l, device:0
chaiml-dpo-training-alb-26034-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-dpo-training-alb-26034-v2-mkmlizer: quantized model in 35.374s
chaiml-dpo-training-alb-26034-v2-mkmlizer: Processed model ChaiML/dpo-training-albert-4n8g in 68.459s
chaiml-dpo-training-alb-26034-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-dpo-training-alb-26034-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-dpo-training-alb-26034-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-dpo-training-alb-26034-v2
chaiml-dpo-training-alb-26034-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-dpo-training-alb-26034-v2/config.json
chaiml-dpo-training-alb-26034-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-dpo-training-alb-26034-v2/special_tokens_map.json
chaiml-dpo-training-alb-26034-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-dpo-training-alb-26034-v2/tokenizer_config.json
chaiml-dpo-training-alb-26034-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-dpo-training-alb-26034-v2/tokenizer.json
chaiml-dpo-training-alb-26034-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-dpo-training-alb-26034-v2/flywheel_model.0.safetensors
chaiml-dpo-training-alb-26034-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.62it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 54.03it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:06, 51.18it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 50.11it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.73it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 50.73it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 51.60it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 53.83it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 49.61it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.24it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 37.35it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 41.95it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 43.41it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 36.72it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:06, 45.26it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 43.06it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.30it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 51.84it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 46.90it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:05, 46.86it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 46.85it/s]
Loading 0:  36%|███▌      | 131/363 [00:02<00:04, 47.61it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:05, 39.18it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 33.36it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 33.84it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.11it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 40.89it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 41.53it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 42.29it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:04, 47.00it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 46.44it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 44.90it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 49.75it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 48.20it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 46.56it/s]
Loading 0:  58%|█████▊    | 210/363 [00:04<00:03, 49.87it/s]
Loading 0:  60%|█████▉    | 216/363 [00:04<00:03, 47.74it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 44.06it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 32.15it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.49it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 38.16it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 39.92it/s]
Loading 0:  68%|██████▊   | 248/363 [00:05<00:02, 38.66it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 46.41it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 46.79it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 39.45it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 47.34it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 46.30it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 44.10it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 48.41it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 47.06it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:20,  2.86it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:15,  3.58it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:11,  4.56it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:05,  7.35it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.80it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 12.28it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 17.05it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.73it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 23.89it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 30.27it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 31.86it/s]
                                                            
Job chaiml-dpo-training-alb-26034-v2-mkmlizer completed after 94.31s with status: succeeded
Stopping job with name chaiml-dpo-training-alb-26034-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.84s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-dpo-training-alb-26034-v2
Waiting for inference service chaiml-dpo-training-alb-26034-v2 to be ready
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission function_lijit_2024-11-26: ('http://zonemercy-lexical-viral-7348-v17-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:39216->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission cgato-nemo-12b-humanize_20284_v4: HTTPConnectionPool(host='cgato-nemo-12b-humanize-20284-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-dpo-training-alb-26034-v2 ready after 351.5179307460785s
Pipeline stage MKMLDeployer completed in 352.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9773492813110352s
Received healthy response to inference request in 1.0561487674713135s
Received healthy response to inference request in 0.8957850933074951s
Received healthy response to inference request in 1.2286911010742188s
Received healthy response to inference request in 1.1779308319091797s
5 requests
0 failed requests
5th percentile: 0.9278578281402587
10th percentile: 0.9599305629730225
20th percentile: 1.0240760326385498
30th percentile: 1.0805051803588868
40th percentile: 1.1292180061340331
50th percentile: 1.1779308319091797
60th percentile: 1.1982349395751952
70th percentile: 1.218539047241211
80th percentile: 1.3784227371215823
90th percentile: 1.6778860092163086
95th percentile: 1.8276176452636717
99th percentile: 1.9474029541015625
mean time: 1.2671810150146485
Pipeline stage StressChecker completed in 7.67s
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 0.72s
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 0.71s
Shutdown handler de-registered
chaiml-dpo-training-alb_26034_v2 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 2835.77s
Shutdown handler de-registered
chaiml-dpo-training-alb_26034_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-dpo-training-alb_26034_v2 status is now torndown due to DeploymentManager action