developer_uid: zonemercy
submission_id: chaiml-snugstable1-5-12_77835_v6
model_name: tempv1-1
model_group: ChaiML/SnugStable1.5-12b
status: torndown
timestamp: 2025-01-08T09:22:27+00:00
num_battles: 5471
num_wins: 2855
celo_rating: 1283.36
family_friendly_score: 0.5920000000000001
family_friendly_standard_error: 0.006950338121271511
submission_type: basic
model_repo: ChaiML/SnugStable1.5-12b0-l1e5r7b25
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6485342640180023, 'latency_mean': 1.5418778359889984, 'latency_p50': 1.5540140867233276, 'latency_p90': 1.6872012138366699}, {'batch_size': 3, 'throughput': 1.2545069359200545, 'latency_mean': 2.3799660384654997, 'latency_p50': 2.3628549575805664, 'latency_p90': 2.6274133920669556}, {'batch_size': 5, 'throughput': 1.562129497160406, 'latency_mean': 3.187088718414307, 'latency_p50': 3.186383008956909, 'latency_p90': 3.6333730220794678}, {'batch_size': 6, 'throughput': 1.6755388888937492, 'latency_mean': 3.56159686923027, 'latency_p50': 3.531597375869751, 'latency_p90': 4.0231749534606935}, {'batch_size': 8, 'throughput': 1.744907479190798, 'latency_mean': 4.547602593898773, 'latency_p50': 4.525103449821472, 'latency_p90': 5.20652334690094}, {'batch_size': 10, 'throughput': 1.8104369555761246, 'latency_mean': 5.479691152572632, 'latency_p50': 5.496082663536072, 'latency_p90': 6.196655225753784}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-1
is_internal_developer: True
language_model: ChaiML/SnugStable1.5-12b0-l1e5r7b25
model_size: 13B
ranking_group: single
throughput_3p7s: 1.7
us_pacific_date: 2025-01-08
win_ratio: 0.5218424419667337
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': ['<|eot_id|>', 'Bot:', '<|im_end|>', '</s>', '\n', '####', 'User:', 'You:'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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-snugstable1-5-12-77835-v6-mkmlizer
Waiting for job on chaiml-snugstable1-5-12-77835-v6-mkmlizer to finish
chaiml-snugstable1-5-12-77835-v6-mkmlizer: Downloaded to shared memory in 36.332s
chaiml-snugstable1-5-12-77835-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcso062tt, device:0
chaiml-snugstable1-5-12-77835-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable1-5-12-77835-v6-mkmlizer: quantized model in 38.993s
chaiml-snugstable1-5-12-77835-v6-mkmlizer: Processed model ChaiML/SnugStable1.5-12b0-l1e5r7b25 in 75.325s
chaiml-snugstable1-5-12-77835-v6-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable1-5-12-77835-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable1-5-12-77835-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable1-5-12-77835-v6
chaiml-snugstable1-5-12-77835-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-77835-v6/config.json
chaiml-snugstable1-5-12-77835-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-77835-v6/special_tokens_map.json
chaiml-snugstable1-5-12-77835-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-77835-v6/tokenizer_config.json
chaiml-snugstable1-5-12-77835-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-77835-v6/tokenizer.json
Job chaiml-snugstable1-5-12-77835-v6-mkmlizer completed after 123.24s with status: succeeded
Stopping job with name chaiml-snugstable1-5-12-77835-v6-mkmlizer
Pipeline stage MKMLizer completed in 123.71s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-snugstable1-5-12-77835-v6
Waiting for inference service chaiml-snugstable1-5-12-77835-v6 to be ready
Inference service chaiml-snugstable1-5-12-77835-v6 ready after 351.6154236793518s
Pipeline stage MKMLDeployer completed in 352.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9605896472930908s
Received healthy response to inference request in 1.5234882831573486s
Received healthy response to inference request in 1.5362160205841064s
Received healthy response to inference request in 1.4729204177856445s
Received healthy response to inference request in 1.7404720783233643s
5 requests
0 failed requests
5th percentile: 1.4830339908599854
10th percentile: 1.4931475639343261
20th percentile: 1.5133747100830077
30th percentile: 1.5260338306427002
40th percentile: 1.5311249256134034
50th percentile: 1.5362160205841064
60th percentile: 1.6179184436798095
70th percentile: 1.6996208667755126
80th percentile: 1.7844955921173096
90th percentile: 1.8725426197052002
95th percentile: 1.9165661334991455
99th percentile: 1.9517849445343018
mean time: 1.646737289428711
Pipeline stage StressChecker completed in 9.51s
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 0.81s
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 0.68s
Shutdown handler de-registered
chaiml-snugstable1-5-12_77835_v6 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-snugstable1-5-12-77835-v6-profiler
Waiting for inference service chaiml-snugstable1-5-12-77835-v6-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 2500.59s
Shutdown handler de-registered
chaiml-snugstable1-5-12_77835_v6 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable1-5-12_77835_v6 status is now torndown due to DeploymentManager action