rirv938-anthropic-40k-2_60007

developer_uid: rirv938

submission_id: rirv938-anthropic-40k-2_60007_v1

model_name: rirv938-anthropic-40k-2_60007_v1

model_group: rirv938/anthropic_40k_24

status: torndown

timestamp: 2025-01-01T19:03:28+00:00

num_battles: 19425

num_wins: 10497

celo_rating: 1302.76

family_friendly_score: 0.5968

family_friendly_standard_error: 0.006937287077813632

submission_type: basic

model_repo: rirv938/anthropic_40k_2496_bo8_85w_b4_2xlora_lr4_v2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6469445608210287, 'latency_mean': 1.5456701231002807, 'latency_p50': 1.5503798723220825, 'latency_p90': 1.7144695520401}, {'batch_size': 3, 'throughput': 1.240807032158504, 'latency_mean': 2.4081250274181367, 'latency_p50': 2.402562141418457, 'latency_p90': 2.6644941091537477}, {'batch_size': 5, 'throughput': 1.526584823507647, 'latency_mean': 3.2522403490543366, 'latency_p50': 3.2536247968673706, 'latency_p90': 3.622279667854309}, {'batch_size': 6, 'throughput': 1.6173938696716268, 'latency_mean': 3.696201117038727, 'latency_p50': 3.684133768081665, 'latency_p90': 4.179702711105347}, {'batch_size': 8, 'throughput': 1.6960801616304664, 'latency_mean': 4.687341923713684, 'latency_p50': 4.740962386131287, 'latency_p90': 5.223176050186157}, {'batch_size': 10, 'throughput': 1.769726424028051, 'latency_mean': 5.616320066452026, 'latency_p50': 5.624338388442993, 'latency_p90': 6.289164304733276}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-40k-2_60007_v1

is_internal_developer: True

language_model: rirv938/anthropic_40k_2496_bo8_85w_b4_2xlora_lr4_v2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.62

us_pacific_date: 2025-01-01

win_ratio: 0.5403861003861004

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '<|end_of_text|>', 'You:'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{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 rirv938-anthropic-40k-2-60007-v1-mkmlizer
Waiting for job on rirv938-anthropic-40k-2-60007-v1-mkmlizer to finish
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-40k-2-60007-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission rirv938-anthropic-40k-2_43413_v3: HTTPConnectionPool(host='rirv938-anthropic-40k-2-43413-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-anthropic-40k-2_32301_v2: HTTPConnectionPool(host='rirv938-anthropic-40k-2-32301-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-anthropic-40k-2_32301_v2: HTTPConnectionPool(host='rirv938-anthropic-40k-2-32301-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-anthropic-40k-2_69835_v2: HTTPConnectionPool(host='rirv938-anthropic-40k-2-69835-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-anthropic-40k-2_69835_v2: HTTPConnectionPool(host='rirv938-anthropic-40k-2-69835-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-anthropic-40k-2-60007-v1-mkmlizer: Downloaded to shared memory in 94.761s
rirv938-anthropic-40k-2-60007-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxulv7ok9, device:0
rirv938-anthropic-40k-2-60007-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission rirv938-anthropic-40k-2_32301_v2: HTTPConnectionPool(host='rirv938-anthropic-40k-2-32301-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-anthropic-40k-2_43413_v3: HTTPConnectionPool(host='rirv938-anthropic-40k-2-43413-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-anthropic-40k-2-60007-v1-mkmlizer: quantized model in 41.469s
rirv938-anthropic-40k-2-60007-v1-mkmlizer: Processed model rirv938/anthropic_40k_2496_bo8_85w_b4_2xlora_lr4_v2 in 136.230s
rirv938-anthropic-40k-2-60007-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-40k-2-60007-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-40k-2-60007-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-40k-2-60007-v1
rirv938-anthropic-40k-2-60007-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-40k-2-60007-v1/config.json
rirv938-anthropic-40k-2-60007-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-40k-2-60007-v1/special_tokens_map.json
rirv938-anthropic-40k-2-60007-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-40k-2-60007-v1/tokenizer_config.json
rirv938-anthropic-40k-2-60007-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-40k-2-60007-v1/tokenizer.json
rirv938-anthropic-40k-2-60007-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-40k-2-60007-v1/flywheel_model.0.safetensors
Job rirv938-anthropic-40k-2-60007-v1-mkmlizer completed after 166.39s with status: succeeded
Stopping job with name rirv938-anthropic-40k-2-60007-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.00s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.56s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-40k-2-60007-v1
Waiting for inference service rirv938-anthropic-40k-2-60007-v1 to be ready
Failed to get response for submission rirv938-anthropic-40k-2_32301_v2: HTTPConnectionPool(host='rirv938-anthropic-40k-2-32301-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-anthropic-40k-2_43413_v3: HTTPConnectionPool(host='rirv938-anthropic-40k-2-43413-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-anthropic-40k-2_32301_v2: HTTPConnectionPool(host='rirv938-anthropic-40k-2-32301-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-anthropic-40k-2_32301_v2: HTTPConnectionPool(host='rirv938-anthropic-40k-2-32301-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-anthropic-40k-2_32301_v2: HTTPConnectionPool(host='rirv938-anthropic-40k-2-32301-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rirv938-anthropic-40k-2-60007-v1 ready after 321.62850069999695s
Pipeline stage MKMLDeployer completed in 322.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.432352304458618s
Received healthy response to inference request in 1.675029993057251s
Received healthy response to inference request in 1.4963469505310059s
Received healthy response to inference request in 1.3854103088378906s
Received healthy response to inference request in 1.6206026077270508s
5 requests
0 failed requests
5th percentile: 1.4075976371765138
10th percentile: 1.4297849655151367
20th percentile: 1.4741596221923827
30th percentile: 1.5211980819702149
40th percentile: 1.5709003448486327
50th percentile: 1.6206026077270508
60th percentile: 1.6423735618591309
70th percentile: 1.664144515991211
80th percentile: 1.8264944553375246
90th percentile: 2.1294233798980713
95th percentile: 2.2808878421783447
99th percentile: 2.4020594120025636
mean time: 1.7219484329223633
Pipeline stage StressChecker completed in 9.90s
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 0.61s
Shutdown handler de-registered
rirv938-anthropic-40k-2_60007_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 0.10s
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 rirv938-anthropic-40k-2-60007-v1-profiler
Waiting for inference service rirv938-anthropic-40k-2-60007-v1-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 2533.61s
Shutdown handler de-registered
rirv938-anthropic-40k-2_60007_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-40k-2_60007_v1 status is now torndown due to DeploymentManager action
rirv938-anthropic-40k-2_60007_v1 status is now torndown due to DeploymentManager action
rirv938-anthropic-40k-2_60007_v1 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message