developer_uid: azuruce
submission_id: chaiml-mistral-nemo-dpo-_6309_v1
model_name: chaiml-mistral-nemo-dpo-_6309_v1
model_group: ChaiML/mistral_nemo_dpo_
status: inactive
timestamp: 2024-12-20T17:26:11+00:00
num_battles: 11742
num_wins: 5624
celo_rating: 1238.18
family_friendly_score: 0.5858
family_friendly_standard_error: 0.006966180589103328
submission_type: basic
model_repo: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-69
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6327310144262345, 'latency_mean': 1.5803910052776338, 'latency_p50': 1.591599702835083, 'latency_p90': 1.7368149518966676}, {'batch_size': 3, 'throughput': 1.2623549281711686, 'latency_mean': 2.3734927105903627, 'latency_p50': 2.373802661895752, 'latency_p90': 2.612684392929077}, {'batch_size': 5, 'throughput': 1.5861962641239165, 'latency_mean': 3.1265450978279112, 'latency_p50': 3.129777193069458, 'latency_p90': 3.496645450592041}, {'batch_size': 6, 'throughput': 1.6850714604425854, 'latency_mean': 3.5312999832630156, 'latency_p50': 3.5456398725509644, 'latency_p90': 4.017284536361695}, {'batch_size': 8, 'throughput': 1.8445029918581342, 'latency_mean': 4.306982661485672, 'latency_p50': 4.326297879219055, 'latency_p90': 4.870209550857544}, {'batch_size': 10, 'throughput': 1.9310265798812778, 'latency_mean': 5.1509737873077395, 'latency_p50': 5.162214994430542, 'latency_p90': 5.83987774848938}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistral-nemo-dpo-_6309_v1
is_internal_developer: True
language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-69
model_size: 13B
ranking_group: single
throughput_3p7s: 1.74
us_pacific_date: 2024-12-20
win_ratio: 0.47896440129449835
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': ['\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-mistral-nemo-dpo-6309-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-6309-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ _____ __ __ ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ /___/ ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ belonging to: ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: Downloaded to shared memory in 49.669s
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_3bskoz0, device:0
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: quantized model in 37.056s
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-69 in 86.725s
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6309-v1
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6309-v1/config.json
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6309-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6309-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6309-v1/tokenizer.json
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6309-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-6309-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 26.59it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:07, 44.11it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 42.51it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 42.47it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:07, 44.34it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:09, 34.51it/s] Loading 0: 11%|█ | 39/363 [00:00<00:07, 42.18it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:07, 41.56it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:07, 41.48it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:07, 43.13it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:07, 40.86it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:11, 25.22it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:09, 30.41it/s] Loading 0: 21%|██ | 75/363 [00:02<00:09, 31.20it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:08, 34.69it/s] Loading 0: 23%|██▎ | 85/363 [00:02<00:07, 36.38it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:07, 38.40it/s] Loading 0: 26%|██▌ | 95/363 [00:02<00:06, 39.93it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:08, 31.98it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:06, 36.96it/s] Loading 0: 31%|███ | 112/363 [00:03<00:06, 41.28it/s] Loading 0: 32%|███▏ | 117/363 [00:03<00:06, 39.30it/s] Loading 0: 34%|███▎ | 122/363 [00:03<00:05, 41.22it/s] Loading 0: 35%|███▍ | 127/363 [00:03<00:06, 34.90it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 42.34it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 42.68it/s] Loading 0: 40%|███▉ | 144/363 [00:04<00:08, 26.15it/s] Loading 0: 41%|████ | 149/363 [00:04<00:07, 28.52it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:05, 36.02it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 33.98it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:05, 35.65it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:05, 37.67it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 33.56it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 40.54it/s] Loading 0: 52%|█████▏ | 188/363 [00:05<00:04, 41.22it/s] Loading 0: 53%|█████▎ | 193/363 [00:05<00:03, 42.58it/s] Loading 0: 55%|█████▍ | 199/363 [00:05<00:04, 40.34it/s] Loading 0: 56%|█████▌ | 204/363 [00:05<00:04, 39.04it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 43.24it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 42.37it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 42.80it/s] Loading 0: 62%|██████▏ | 225/363 [00:06<00:05, 26.81it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 28.47it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 35.62it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 37.15it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 38.15it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 40.17it/s] Loading 0: 71%|███████ | 257/363 [00:07<00:03, 32.40it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 39.37it/s] Loading 0: 74%|███████▍ | 269/363 [00:07<00:02, 39.93it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 40.41it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:01, 42.15it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 34.81it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 41.21it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 40.48it/s] Loading 0: 83%|████████▎ | 301/363 [00:08<00:01, 41.45it/s] Loading 0: 84%|████████▍ | 306/363 [00:14<00:23, 2.46it/s] Loading 0: 85%|████████▌ | 310/363 [00:15<00:16, 3.19it/s] Loading 0: 87%|████████▋ | 314/363 [00:15<00:11, 4.17it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:07, 5.85it/s] Loading 0: 89%|████████▉ | 323/363 [00:15<00:05, 7.53it/s] Loading 0: 91%|█████████ | 329/363 [00:15<00:03, 10.96it/s] Loading 0: 92%|█████████▏| 335/363 [00:15<00:01, 14.62it/s] Loading 0: 94%|█████████▎| 340/363 [00:15<00:01, 18.06it/s] Loading 0: 96%|█████████▌| 347/363 [00:15<00:00, 24.23it/s] Loading 0: 97%|█████████▋| 353/363 [00:15<00:00, 27.54it/s] Loading 0: 99%|█████████▊| 358/363 [00:16<00:00, 30.33it/s]
Job chaiml-mistral-nemo-dpo-6309-v1-mkmlizer completed after 114.86s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-6309-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-dpo-6309-v1
Waiting for inference service chaiml-mistral-nemo-dpo-6309-v1 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
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
Inference service chaiml-mistral-nemo-dpo-6309-v1 ready after 260.8941013813019s
Pipeline stage MKMLDeployer completed in 261.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.84535813331604s
Received healthy response to inference request in 1.4684526920318604s
Received healthy response to inference request in 1.46323561668396s
Received healthy response to inference request in 0.8747007846832275s
Received healthy response to inference request in 1.510406732559204s
5 requests
0 failed requests
5th percentile: 0.992407751083374
10th percentile: 1.1101147174835204
20th percentile: 1.3455286502838135
30th percentile: 1.4642790317535401
40th percentile: 1.4663658618927002
50th percentile: 1.4684526920318604
60th percentile: 1.485234308242798
70th percentile: 1.5020159244537354
80th percentile: 1.5773970127105714
90th percentile: 1.7113775730133056
95th percentile: 1.7783678531646727
99th percentile: 1.8319600772857665
mean time: 1.4324307918548584
Pipeline stage StressChecker completed in 8.52s
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 0.68s
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 0.67s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_6309_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 2437.92s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_6309_v1 status is now inactive due to auto deactivation removed underperforming models