developer_uid: azuruce
submission_id: chaiml-mistral-nemo-dpo-_1624_v2
model_name: chaiml-mistral-nemo-dpo-_1624_v2
model_group: ChaiML/mistral_nemo_dpo_
status: inactive
timestamp: 2024-12-20T23:18:41+00:00
num_battles: 12347
num_wins: 5793
celo_rating: 1222.13
family_friendly_score: 0.5993999999999999
family_friendly_standard_error: 0.006929929869775018
submission_type: basic
model_repo: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-1173
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6356105690966756, 'latency_mean': 1.5732291388511657, 'latency_p50': 1.561233401298523, 'latency_p90': 1.7316223621368407}, {'batch_size': 3, 'throughput': 1.2693552737565121, 'latency_mean': 2.3576029682159425, 'latency_p50': 2.34713876247406, 'latency_p90': 2.5964920282363892}, {'batch_size': 5, 'throughput': 1.6084979508371926, 'latency_mean': 3.0861167347431184, 'latency_p50': 3.0837079286575317, 'latency_p90': 3.393415117263794}, {'batch_size': 6, 'throughput': 1.720418664834361, 'latency_mean': 3.4779819583892824, 'latency_p50': 3.4841631650924683, 'latency_p90': 3.936330723762512}, {'batch_size': 8, 'throughput': 1.8730388677567429, 'latency_mean': 4.2367188465595245, 'latency_p50': 4.231796503067017, 'latency_p90': 4.7572636842727665}, {'batch_size': 10, 'throughput': 1.9432134032718997, 'latency_mean': 5.102375696897507, 'latency_p50': 5.160101890563965, 'latency_p90': 5.758610224723816}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistral-nemo-dpo-_1624_v2
is_internal_developer: True
language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-1173
model_size: 13B
ranking_group: single
throughput_3p7s: 1.78
us_pacific_date: 2024-12-20
win_ratio: 0.46918279744067387
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-1624-v2-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-1624-v2-mkmlizer to finish
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: Downloaded to shared memory in 37.109s
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdrg9zon2, device:0
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: quantized model in 38.324s
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-1173 in 75.433s
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1624-v2
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1624-v2/config.json
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1624-v2/special_tokens_map.json
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1624-v2/tokenizer_config.json
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1624-v2/tokenizer.json
chaiml-mistral-nemo-dpo-1624-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1624-v2/flywheel_model.0.safetensors
Job chaiml-mistral-nemo-dpo-1624-v2-mkmlizer completed after 104.47s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-1624-v2-mkmlizer
Pipeline stage MKMLizer completed in 104.94s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-dpo-1624-v2
Waiting for inference service chaiml-mistral-nemo-dpo-1624-v2 to be ready
Failed to get response for submission function_pajeb_2024-11-26: ('http://chaiml-elo-alignment-run-3-v44-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:59778->127.0.0.1:8080: read: connection reset by peer\n')
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-1624-v2 ready after 411.37316274642944s
Pipeline stage MKMLDeployer completed in 411.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.107293128967285s
Received healthy response to inference request in 0.9996809959411621s
Received healthy response to inference request in 1.3484351634979248s
Received healthy response to inference request in 1.3915126323699951s
Received healthy response to inference request in 1.4591598510742188s
5 requests
0 failed requests
5th percentile: 1.0694318294525147
10th percentile: 1.1391826629638673
20th percentile: 1.2786843299865722
30th percentile: 1.3570506572723389
40th percentile: 1.374281644821167
50th percentile: 1.3915126323699951
60th percentile: 1.4185715198516846
70th percentile: 1.4456304073333741
80th percentile: 1.5887865066528322
90th percentile: 1.8480398178100588
95th percentile: 1.9776664733886717
99th percentile: 2.0813677978515623
mean time: 1.461216354370117
Pipeline stage StressChecker completed in 8.63s
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 0.64s
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 0.70s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_1624_v2 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-nemo-dpo-1624-v2-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-1624-v2-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 2204.62s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_1624_v2 status is now inactive due to auto deactivation removed underperforming models