submission_id: azazelle-l3-hecate-8b-v1-1_v2
developer_uid: Azazelle
alignment_samples: 0
best_of: 16
celo_rating: 1218.07
display_name: Azazelle-L3-Hecate-8B-v1_1
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.15, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Azazelle/L3-Hecate-8B-v1.1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Azazelle/L3-Hecate-8B-v1
model_name: Azazelle-L3-Hecate-8B-v1_1
model_num_parameters: 8030261248.0
model_repo: Azazelle/L3-Hecate-8B-v1.1
model_size: 8B
num_battles: 173117
num_wins: 87890
propriety_score: 0.707430701141393
propriety_total_count: 8586.0
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-16T00:25:36+00:00
us_pacific_date: 2024-07-15
win_ratio: 0.5076913301408874
Resubmit model
Running pipeline stage MKMLizer
Starting job with name azazelle-l3-hecate-8b-v1-1-v2-mkmlizer
Waiting for job on azazelle-l3-hecate-8b-v1-1-v2-mkmlizer to finish
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║     _____            __           __                                ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║       /___/                                                         ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║  Version: 0.9.5.post2                                               ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║  https://mk1.ai                                                     ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║  belonging to:                                                      ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: Downloaded to shared memory in 47.130s
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: lm_head.weight torch.Size([139542528])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.embed_tokens.weight torch.Size([139542528])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.0.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.0.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.0.mlp.up_gate_proj.weight torch.Size([23855104])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.0.post_attention_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.0.self_attn.o_proj.weight torch.Size([3407872])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.0.self_attn.qkv_proj.weight torch.Size([5111808])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.1.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.1.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.1.mlp.up_gate_proj.weight torch.Size([23855104])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.1.post_attention_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.1.self_attn.o_proj.weight torch.Size([3407872])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.1.self_attn.qkv_proj.weight torch.Size([5111808])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.10.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.10.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.10.mlp.up_gate_proj.weight torch.Size([23855104])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.10.post_attention_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.10.self_attn.o_proj.weight torch.Size([3407872])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.10.self_attn.qkv_proj.weight torch.Size([5111808])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.11.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.11.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.11.mlp.up_gate_proj.weight torch.Size([23855104])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.11.post_attention_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.11.self_attn.o_proj.weight torch.Size([3407872])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.11.self_attn.qkv_proj.weight torch.Size([5111808])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.12.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.12.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.12.mlp.up_gate_proj.weight torch.Size([23855104])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.12.post_attention_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.12.self_attn.o_proj.weight torch.Size([3407872])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.12.self_attn.qkv_proj.weight torch.Size([5111808])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.13.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.13.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.13.mlp.up_gate_proj.weight torch.Size([23855104])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.13.post_attention_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.13.self_attn.o_proj.weight torch.Size([3407872])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.13.self_attn.qkv_proj.weight torch.Size([5111808])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.14.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.14.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.14.mlp.up_gate_proj.weight torch.Size([23855104])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.14.post_attention_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.14.self_attn.o_proj.weight torch.Size([3407872])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.14.self_attn.qkv_proj.weight torch.Size([5111808])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.15.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.15.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.15.mlp.up_gate_proj.weight torch.Size([23855104])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.15.post_attention_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.15.self_attn.o_proj.weight torch.Size([3407872])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.15.self_attn.qkv_proj.weight torch.Size([5111808])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.16.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.16.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.16.mlp.up_gate_proj.weight torch.Size([23855104])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.16.post_attention_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.16.self_attn.o_proj.weight torch.Size([3407872])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.16.self_attn.qkv_proj.weight torch.Size([5111808])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.17.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.17.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.17.mlp.up_gate_proj.weight torch.Size([23855104])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.17.post_attention_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.17.self_attn.o_proj.weight torch.Size([3407872])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.17.self_attn.qkv_proj.weight torch.Size([5111808])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.18.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.18.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.18.mlp.up_gate_proj.weight torch.Size([23855104])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.18.post_attention_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.18.self_attn.o_proj.weight torch.Size([3407872])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.18.self_attn.qkv_proj.weight torch.Size([5111808])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.19.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.19.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.19.mlp.up_gate_proj.weight torch.Size([23855104])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.19.post_attention_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.19.self_attn.o_proj.weight torch.Size([3407872])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.19.self_attn.qkv_proj.weight torch.Size([5111808])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.2.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.2.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.2.mlp.up_gate_proj.weight torch.Size([23855104])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.2.post_attention_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.2.self_attn.o_proj.weight torch.Size([3407872])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.2.self_attn.qkv_proj.weight torch.Size([5111808])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.20.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.20.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.20.mlp.up_gate_proj.weight torch.Size([23855104])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.20.post_attention_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.20.self_attn.o_proj.weight torch.Size([3407872])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.20.self_attn.qkv_proj.weight torch.Size([5111808])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.21.input_layernorm.weight torch.Size([4096])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: model.layers.21.mlp.down_proj.weight torch.Size([11927552])
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: 72/291 [00:09<00:03, 37.27it/s]
                                                            

Loading 0:  59%|█████▉    | 173/291 [00:09<00:03, 37.27it/s]
                                                            

Loading 0:  60%|█████▉    | 174/291 [00:09<00:03, 37.27it/s]
                                                            

Loading 0:  60%|██████    | 176/291 [00:09<00:03, 37.27it/s]
                                                            

Loading 0:  61%|██████    | 177/291 [00:09<00:03, 37.27it/s]
Loading 0:  61%|██████    | 178/291 [00:09<00:02, 39.77it/s]
                                                            

Loading 0:  62%|██████▏   | 179/291 [00:09<00:02, 39.77it/s]
                                                            

Loading 0:  62%|██████▏   | 181/291 [00:09<00:02, 39.77it/s]
                                                            

Loading 0:  63%|██████▎   | 182/291 [00:09<00:02, 39.77it/s]
                                                            

Loading 0:  63%|██████▎   | 183/291 [00:09<00:02, 39.77it/s]
Loading 0:  64%|██████▎   | 185/291 [00:09<00:02, 44.92it/s]
                                                            

Loading 0:  64%|██████▎   | 185/291 [00:09<00:02, 44.92it/s]
                                                            

Loading 0:  64%|██████▍   | 186/291 [00:09<00:02, 44.92it/s]
                                                            

Loading 0:  65%|██████▍   | 188/291 [00:09<00:02, 44.92it/s]
                                                            

Loading 0:  65%|██████▌   | 190/291 [00:09<00:02, 44.92it/s]
                                                            

Loading 0:  66%|██████▌   | 191/291 [00:09<00:02, 44.92it/s]
                                                            

Loading 0:  66%|██████▌   | 192/291 [00:09<00:02, 44.92it/s]
Loading 0:  66%|██████▋   | 193/291 [00:09<00:01, 51.93it/s]
                                                            

Loading 0:  67%|██████▋   | 194/291 [00:09<00:01, 51.93it/s]
                                                            

Loading 0:  67%|██████▋   | 195/291 [00:09<00:01, 51.93it/s]
                                                            

Loading 0:  68%|██████▊   | 197/291 [00:09<00:01, 51.93it/s]
                                                            

Loading 0:  68%|██████▊   | 199/291 [00:10<00:01, 51.93it/s]
Loading 0:  69%|██████▊   | 200/291 [00:10<00:01, 55.66it/s]
                                                            

Loading 0:  69%|██████▊   | 200/291 [00:10<00:01, 55.66it/s]
                                                            

Loading 0:  69%|██████▉   | 201/291 [00:10<00:01, 55.66it/s]
                                                            

Loading 0:  70%|██████▉   | 203/291 [00:10<00:01, 55.66it/s]
                                                            

Loading 0:  70%|███████   | 204/291 [00:10<00:01, 55.66it/s]
                                                            

Loading 0:  71%|███████   | 206/291 [00:10<00:01, 55.66it/s]
Loading 0:  71%|███████   | 207/291 [00:10<00:01, 55.04it/s]
                                                            

Loading 0:  71%|███████▏  | 208/291 [00:10<00:01, 55.04it/s]
                                                            

Loading 0:  72%|███████▏  | 209/291 [00:10<00:01, 55.04it/s]
                                                            

Loading 0:  72%|███████▏  | 210/291 [00:10<00:01, 55.04it/s]
                                                            

Loading 0:  73%|███████▎  | 212/291 [00:10<00:01, 55.04it/s]
                                                            

Loading 0:  73%|███████▎  | 213/291 [00:10<00:01, 55.04it/s]
Loading 0:  74%|███████▎  | 214/291 [00:10<00:02, 29.00it/s]
                                                            

Loading 0:  74%|███████▍  | 215/291 [00:10<00:02, 29.00it/s]
                                                            

Loading 0:  75%|███████▍  | 217/291 [00:10<00:02, 29.00it/s]
                                                            

Loading 0:  75%|███████▍  | 218/291 [00:10<00:02, 29.00it/s]
                                                            

Loading 0:  75%|███████▌  | 219/291 [00:10<00:02, 29.00it/s]
Loading 0:  76%|███████▌  | 221/291 [00:10<00:02, 34.84it/s]
                                                            

Loading 0:  76%|███████▌  | 221/291 [00:10<00:02, 34.84it/s]
                                                            

Loading 0:  76%|███████▋  | 222/291 [00:10<00:01, 34.84it/s]
                                                            

Loading 0:  77%|███████▋  | 224/291 [00:10<00:01, 34.84it/s]
                                                            

Loading 0:  78%|███████▊  | 226/291 [00:10<00:01, 34.84it/s]
                                                            

Loading 0:  78%|███████▊  | 227/291 [00:10<00:01, 34.84it/s]
                                                            

Loading 0:  78%|███████▊  | 228/291 [00:10<00:01, 34.84it/s]
Loading 0:  79%|███████▊  | 229/291 [00:10<00:01, 42.44it/s]
                                                            

Loading 0:  79%|███████▉  | 230/291 [00:10<00:01, 42.44it/s]
                                                            

Loading 0:  79%|███████▉  | 231/291 [00:10<00:01, 42.44it/s]
                                                            

Loading 0:  80%|████████  | 233/291 [00:10<00:01, 42.44it/s]
                                                            

Loading 0:  81%|████████  | 235/291 [00:10<00:01, 42.44it/s]
Loading 0:  81%|████████  | 236/291 [00:10<00:01, 47.80it/s]
                                                            

Loading 0:  81%|████████  | 236/291 [00:10<00:01, 47.80it/s]
                                                            

Loading 0:  81%|████████▏ | 237/291 [00:10<00:01, 47.80it/s]
                                                            

Loading 0:  82%|████████▏ | 239/291 [00:11<00:01, 47.80it/s]
                                                            

Loading 0:  82%|████████▏ | 240/291 [00:11<00:01, 47.80it/s]
                                                            

Loading 0:  83%|████████▎ | 242/291 [00:11<00:01, 47.80it/s]
Loading 0:  84%|████████▎ | 243/291 [00:11<00:00, 50.14it/s]
                                                            

Loading 0:  84%|████████▍ | 244/291 [00:11<00:00, 50.14it/s]
                                                            

Loading 0:  84%|████████▍ | 245/291 [00:11<00:00, 50.14it/s]
                                                            

Loading 0:  85%|████████▍ | 246/291 [00:11<00:00, 50.14it/s]
                                                            

Loading 0:  85%|████████▌ | 248/291 [00:11<00:00, 50.14it/s]
                                                            

Loading 0:  86%|████████▌ | 249/291 [00:11<00:00, 50.14it/s]
Loading 0:  86%|████████▌ | 250/291 [00:11<00:00, 51.31it/s]
                                                            

Loading 0:  86%|████████▋ | 251/291 [00:11<00:00, 51.31it/s]
                                                            

Loading 0:  87%|████████▋ | 253/291 [00:11<00:00, 51.31it/s]
                                                            

Loading 0:  87%|████████▋ | 254/291 [00:11<00:00, 51.31it/s]
                                                            

Loading 0:  88%|████████▊ | 255/291 [00:11<00:00, 51.31it/s]
Loading 0:  88%|████████▊ | 257/291 [00:11<00:00, 55.36it/s]
                                                            

Loading 0:  88%|████████▊ | 257/291 [00:11<00:00, 55.36it/s]
                                                            

Loading 0:  89%|████████▊ | 258/291 [00:11<00:00, 55.36it/s]
                                                            

Loading 0:  89%|████████▉ | 260/291 [00:11<00:00, 55.36it/s]
                                                            

Loading 0:  90%|█████████ | 262/291 [00:11<00:00, 55.36it/s]
                                                            

Loading 0:  90%|█████████ | 263/291 [00:11<00:00, 55.36it/s]
                                                            

Loading 0:  91%|█████████ | 264/291 [00:11<00:00, 55.36it/s]
Loading 0:  91%|█████████ | 265/291 [00:11<00:00, 61.21it/s]
                                                            

Loading 0:  91%|█████████▏| 266/291 [00:11<00:00, 61.21it/s]
                                                            

Loading 0:  92%|█████████▏| 267/291 [00:11<00:00, 61.21it/s]
                                                            

Loading 0:  92%|█████████▏| 269/291 [00:11<00:00, 61.21it/s]
                                                            

Loading 0:  93%|█████████▎| 271/291 [00:11<00:00, 61.21it/s]
Loading 0:  93%|█████████▎| 272/291 [00:11<00:00, 32.35it/s]
                                                            

Loading 0:  93%|█████████▎| 272/291 [00:11<00:00, 32.35it/s]
                                                            

Loading 0:  94%|█████████▍| 273/291 [00:11<00:00, 32.35it/s]
                                                            

Loading 0:  95%|█████████▍| 275/291 [00:11<00:00, 32.35it/s]
                                                            

Loading 0:  95%|█████████▍| 276/291 [00:11<00:00, 32.35it/s]
Loading 0:  96%|█████████▌| 278/291 [00:11<00:00, 36.19it/s]
                                                            

Loading 0:  96%|█████████▌| 278/291 [00:12<00:00, 36.19it/s]
                                                            

Loading 0:  96%|█████████▌| 280/291 [00:12<00:00, 36.19it/s]
                                                            

Loading 0:  97%|█████████▋| 281/291 [00:12<00:00, 36.19it/s]
                                                            

Loading 0:  97%|█████████▋| 282/291 [00:12<00:00, 36.19it/s]
                                                            

Loading 0:  98%|█████████▊| 284/291 [00:12<00:00, 36.19it/s]
Loading 0:  98%|█████████▊| 285/291 [00:12<00:00, 40.15it/s]
                                                            

Loading 0:  98%|█████████▊| 285/291 [00:12<00:00, 40.15it/s]
                                                            

Loading 0:  99%|█████████▊| 287/291 [00:12<00:00, 40.15it/s]
                                                            

Loading 0:  99%|█████████▉| 289/291 [00:12<00:00, 40.15it/s]
                                                            

Loading 0: 100%|█████████▉| 290/291 [00:12<00:00, 40.15it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: quantized model in 31.939s
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: Processed model Azazelle/L3-Hecate-8B-v1.1 in 79.070s
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: creating bucket guanaco-mkml-models
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-1-v2
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-1-v2/flywheel_model.0.safetensors
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: Saving duration: 0.522s
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.862s
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: creating bucket guanaco-reward-models
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-1-v2_reward
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-1-v2_reward/config.json
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-1-v2_reward/tokenizer_config.json
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-1-v2_reward/special_tokens_map.json
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-1-v2_reward/merges.txt
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-1-v2_reward/vocab.json
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-1-v2_reward/tokenizer.json
azazelle-l3-hecate-8b-v1-1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-1-v2_reward/reward.tensors
Job azazelle-l3-hecate-8b-v1-1-v2-mkmlizer completed after 111.79s with status: succeeded
Stopping job with name azazelle-l3-hecate-8b-v1-1-v2-mkmlizer
Pipeline stage MKMLizer completed in 112.86s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service azazelle-l3-hecate-8b-v1-1-v2
Waiting for inference service azazelle-l3-hecate-8b-v1-1-v2 to be ready
Inference service azazelle-l3-hecate-8b-v1-1-v2 ready after 40.29530739784241s
Pipeline stage ISVCDeployer completed in 47.57s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.243551254272461s
Received healthy response to inference request in 1.3808071613311768s
Received healthy response to inference request in 1.3110301494598389s
Received healthy response to inference request in 1.2887091636657715s
Received healthy response to inference request in 1.2517540454864502s
5 requests
0 failed requests
5th percentile: 1.2591450691223145
10th percentile: 1.2665360927581788
20th percentile: 1.2813181400299072
30th percentile: 1.293173360824585
40th percentile: 1.3021017551422118
50th percentile: 1.3110301494598389
60th percentile: 1.3389409542083741
70th percentile: 1.3668517589569091
80th percentile: 1.5533559799194339
90th percentile: 1.8984536170959474
95th percentile: 2.071002435684204
99th percentile: 2.2090414905548097
mean time: 1.4951703548431396
Pipeline stage StressChecker completed in 8.53s
azazelle-l3-hecate-8b-v1-1_v2 status is now deployed due to DeploymentManager action
azazelle-l3-hecate-8b-v1-1_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of azazelle-l3-hecate-8b-v1-1_v2
Running pipeline stage ISVCDeleter
Checking if service azazelle-l3-hecate-8b-v1-1-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.27s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key azazelle-l3-hecate-8b-v1-1-v2/config.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-1-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-1-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-1-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-1-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key azazelle-l3-hecate-8b-v1-1-v2_reward/config.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-1-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-1-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-1-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-1-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-1-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-1-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.35s
azazelle-l3-hecate-8b-v1-1_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics