Running pipeline stage MKMLizer
Starting job with name trace2333-andrij-llama2-v0-v1-mkmlizer
Waiting for job on trace2333-andrij-llama2-v0-v1-mkmlizer to finish
trace2333-andrij-llama2-v0-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ _____ __ __ ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ /___/ ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ Version: 0.9.5.post2 ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ https://mk1.ai ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ belonging to: ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ Chai Research Corp. ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ║ ║
trace2333-andrij-llama2-v0-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission cgato-l3-thespice-8b-dpo_6378_v2azazelle-l3-tyche-8b-v1-0_v2: no entry with id "cgato-l3-thespice-8b-dpo_6378_v2azazelle-l3-tyche-8b-v1-0_v2" found on database!
Failed to get response for submission cgato-l3-thespice-8b-dpo_6378_v2azazelle-l3-tyche-8b-v1-0_v2: no entry with id "cgato-l3-thespice-8b-dpo_6378_v2azazelle-l3-tyche-8b-v1-0_v2" found on database!
Failed to get response for submission v000000-l3-8b-poppy-moon_1166_v: no entry with id "v000000-l3-8b-poppy-moon_1166_v" found on database!
Failed to get response for submission v000000-l3-8b-poppy-moon_1166_v: no entry with id "v000000-l3-8b-poppy-moon_1166_v" found on database!
Failed to get response for submission cgato-l3-thespice-8b-dpo_6378_v2azazelle-l3-tyche-8b-v1-0_v2: no entry with id "cgato-l3-thespice-8b-dpo_6378_v2azazelle-l3-tyche-8b-v1-0_v2" found on database!
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.27.self_attn.o_proj.weight torch.Size([3407872])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.27.self_attn.qkv_proj.weight torch.Size([10223616])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.28.input_layernorm.weight torch.Size([4096])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.28.mlp.down_proj.weight torch.Size([9158656])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.28.mlp.up_gate_proj.weight torch.Size([18317312])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.28.post_attention_layernorm.weight torch.Size([4096])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.28.self_attn.o_proj.weight torch.Size([3407872])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.28.self_attn.qkv_proj.weight torch.Size([10223616])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.29.self_attn.o_proj.weight torch.Size([3407872])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.29.self_attn.qkv_proj.weight torch.Size([10223616])
trace2333-andrij-llama2-v0-v1-mkmlizer: lm_head.weight torch.Size([34816000])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.29.input_layernorm.weight torch.Size([4096])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.29.mlp.down_proj.weight torch.Size([9158656])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.29.mlp.up_gate_proj.weight torch.Size([18317312])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.29.post_attention_layernorm.weight torch.Size([4096])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.30.input_layernorm.weight torch.Size([4096])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.30.mlp.down_proj.weight torch.Size([9158656])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.30.mlp.up_gate_proj.weight torch.Size([18317312])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.30.post_attention_layernorm.weight torch.Size([4096])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.30.self_attn.o_proj.weight torch.Size([3407872])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.30.self_attn.qkv_proj.weight torch.Size([10223616])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.31.input_layernorm.weight torch.Size([4096])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.31.mlp.down_proj.weight torch.Size([9158656])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.31.mlp.up_gate_proj.weight torch.Size([18317312])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.31.post_attention_layernorm.weight torch.Size([4096])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.31.self_attn.o_proj.weight torch.Size([3407872])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.layers.31.self_attn.qkv_proj.weight torch.Size([10223616])
trace2333-andrij-llama2-v0-v1-mkmlizer: model.norm.weight torch.Size([4096])
trace2333-andrij-llama2-v0-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-andrij-llama2-v0-v1-mkmlizer: Saving duration: 0.558s
trace2333-andrij-llama2-v0-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.713s
trace2333-andrij-llama2-v0-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-andrij-llama2-v0-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-andrij-llama2-v0-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-andrij-llama2-v0-v1_reward
trace2333-andrij-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-andrij-llama2-v0-v1_reward/config.json
trace2333-andrij-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-andrij-llama2-v0-v1_reward/tokenizer_config.json
trace2333-andrij-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-andrij-llama2-v0-v1_reward/special_tokens_map.json
trace2333-andrij-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-andrij-llama2-v0-v1_reward/merges.txt
trace2333-andrij-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-andrij-llama2-v0-v1_reward/vocab.json
trace2333-andrij-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-andrij-llama2-v0-v1_reward/tokenizer.json
trace2333-andrij-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-andrij-llama2-v0-v1_reward/reward.tensors
Job trace2333-andrij-llama2-v0-v1-mkmlizer completed after 94.31s with status: succeeded
Stopping job with name trace2333-andrij-llama2-v0-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.60s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-andrij-llama2-v0-v1
Waiting for inference service trace2333-andrij-llama2-v0-v1 to be ready
Inference service trace2333-andrij-llama2-v0-v1 ready after 30.30545735359192s
Pipeline stage ISVCDeployer completed in 37.72s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8436086177825928s
Received healthy response to inference request in 0.8657355308532715s
Received healthy response to inference request in 1.020402431488037s
Received healthy response to inference request in 1.1446130275726318s
Received healthy response to inference request in 0.8754827976226807s
5 requests
0 failed requests
5th percentile: 0.8676849842071533
10th percentile: 0.8696344375610352
20th percentile: 0.8735333442687988
30th percentile: 0.9044667243957519
40th percentile: 0.9624345779418946
50th percentile: 1.020402431488037
60th percentile: 1.070086669921875
70th percentile: 1.1197709083557128
80th percentile: 1.284412145614624
90th percentile: 1.5640103816986084
95th percentile: 1.7038094997406006
99th percentile: 1.8156487941741943
mean time: 1.1499684810638429
Pipeline stage StressChecker completed in 6.82s
trace2333-andrij-llama2-v0_v1 status is now deployed due to DeploymentManager action
trace2333-andrij-llama2-v0_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-andrij-llama2-v0_v1
Running pipeline stage ISVCDeleter
Checking if service trace2333-andrij-llama2-v0-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.60s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-andrij-llama2-v0-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-andrij-llama2-v0-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-andrij-llama2-v0-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-andrij-llama2-v0-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-andrij-llama2-v0-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key trace2333-andrij-llama2-v0-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-andrij-llama2-v0-v1_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-andrij-llama2-v0-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-andrij-llama2-v0-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-andrij-llama2-v0-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-andrij-llama2-v0-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-andrij-llama2-v0-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-andrij-llama2-v0-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.63s
trace2333-andrij-llama2-v0_v1 status is now torndown due to DeploymentManager action