submission_id: cycy233-l3-bdpo-v8-c4_v1
developer_uid: shiroe40
alignment_samples: 0
best_of: 16
celo_rating: 1183.39
display_name: auto
formatter: {'memory_template': "<|begin_of_text|><|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': 0.6, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: cycy233/L3-bdpo-v8-c4
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-bdpo-v8-c4
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-bdpo-v8-c4
model_size: 8B
num_battles: 70454
num_wins: 34436
propriety_score: 0.7475145697634556
propriety_total_count: 5834.0
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: 2024-07-15T07:50:37+00:00
us_pacific_date: 2024-07-15
win_ratio: 0.48877281630567465
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bdpo-v8-c4-v1-mkmlizer
Waiting for job on cycy233-l3-bdpo-v8-c4-v1-mkmlizer to finish
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ /___/ ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ Version: 0.9.5.post2 ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ║ ║
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: Downloaded to shared memory in 37.517s
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.embed_tokens.weight torch.Size([139542528])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.0.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.0.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.0.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.0.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.0.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.0.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.1.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.1.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.1.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.1.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.1.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.1.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.2.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.2.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.2.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.2.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.2.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.2.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.3.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.3.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.3.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.3.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.3.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.3.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.4.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.4.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.4.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.4.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.4.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.4.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.5.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.5.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.5.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.5.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.5.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.5.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.6.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.6.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.6.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.6.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.6.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.6.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.7.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.7.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.7.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.7.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.7.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.7.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.8.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.8.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.8.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.8.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.8.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.8.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.10.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.10.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.10.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.10.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.10.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.10.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.11.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.11.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.11.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.11.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.11.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.11.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.12.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.12.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.12.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.12.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.12.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.12.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.13.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.13.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.13.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.13.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.13.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.13.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.14.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.14.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.14.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.14.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.14.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.14.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.15.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.15.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.15.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.15.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.15.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.15.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.16.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.16.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.16.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.16.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.16.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.16.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.17.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.17.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.17.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.17.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.17.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.17.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.18.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.18.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.18.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.18.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.18.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.18.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.19.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.19.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.19.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.19.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.19.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.19.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.20.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.20.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.9.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.9.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.9.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.9.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.9.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.9.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.20.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.20.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.20.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.20.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.21.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.21.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.21.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.21.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.21.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.21.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.22.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.22.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.22.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.22.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.22.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.22.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.23.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.23.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.23.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.23.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.23.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.23.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.24.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.24.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.24.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 0%| | 1/291 [00:00<00:00, 431.34it/s] Loading 0: 1%| | 2/291 [00:00<00:03, 77.04it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:04, 58.80it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:03, 72.95it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:03, 92.47it/s] Loading 0: 3%|▎ | 9/291 [00:00<00:02, 107.93it/s] Loading 0: 3%|▎ | 10/291 [00:00<00:02, 119.44it/s] Loading 0: 4%|▍ | 11/291 [00:00<00:02, 108.44it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 118.13it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 118.13it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 118.13it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:02, 118.13it/s] Loading 0: 6%|▌ | 18/291 [00:00<00:02, 118.13it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:02, 118.13it/s] Loading 0: 7%|▋ | 20/291 [00:00<00:02, 118.13it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:02, 118.13it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:02, 118.13it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 114.62it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:02, 114.62it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:02, 114.62it/s] Loading 0: 10%|▉ | 28/291 [00:00<00:02, 114.62it/s] Loading 0: 10%|▉ | 29/291 [00:00<00:02, 114.62it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 114.62it/s] Loading 0: 11%|█ | 32/291 [00:00<00:02, 114.62it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:02, 114.62it/s] Loading 0: 12%|█▏ | 36/291 [00:00<00:02, 114.62it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:02, 114.62it/s] Loading 0: 13%|█▎ | 38/291 [00:00<00:02, 114.62it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:01, 127.17it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:01, 127.17it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:01, 127.17it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:01, 127.17it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 127.17it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:01, 127.17it/s] Loading 0: 16%|█▌ | 47/291 [00:00<00:01, 127.17it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 127.17it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 127.17it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 90.57it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 90.57it/s] Loading 0: 19%|█▊ | 54/291 [00:00<00:02, 90.57it/s] Loading 0: 19%|█▉ | 55/291 [00:00<00:02, 90.57it/s] Loading 0: 19%|█▉ | 56/291 [00:00<00:02, 90.57it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 90.57it/s] Loading 0: 20%|██ | 59/291 [00:00<00:02, 90.57it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 90.57it/s] Loading 0: 22%|██▏ | 63/291 [00:00<00:02, 95.76it/s] Loading 0: 22%|██▏ | 63/291 [00:00<00:02, 95.76it/s] Loading 0: 22%|██▏ | 64/291 [00:00<00:02, 95.76it/s] Loading 0: 22%|██▏ | 65/291 [00:00<00:02, 95.76it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 95.76it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:02, 95.76it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 95.76it/s] Loading 0: 25%|██▍ | 72/291 [00:00<00:02, 95.76it/s] Loading 0: 25%|██▌ | 73/291 [00:00<00:02, 95.76it/s] Loading 0: 25%|██▌ | 74/291 [00:00<00:02, 98.52it/s] Loading 0: 25%|██▌ | 74/291 [00:00<00:02, 98.52it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 98.52it/s] Loading 0: 26%|██▋ | 77/291 [00:00<00:02, 98.52it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:02, 98.52it/s] Loading 0: 28%|██▊ | 81/291 [00:00<00:02, 98.52it/s] Loading 0: 28%|██▊ | 82/291 [00:01<00:02, 98.52it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 98.52it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:04, 46.33it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:04, 46.33it/s] Loading 0: 30%|██▉ | 86/291 [00:01<00:04, 46.33it/s] Loading 0: 30%|███ | 88/291 [00:01<00:04, 46.33it/s] Loading 0: 31%|███ | 90/291 [00:01<00:04, 46.33it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:04, 46.33it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:04, 46.33it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:04, 46.33it/s] Loading 0: 33%|███▎ | 95/291 [00:01<00:04, 46.33it/s] Loading 0: 33%|███▎ | 97/291 [00:01<00:03, 57.78it/s] Loading 0: 33%|███▎ | 97/291 [00:01<00:03, 57.78it/s] Loading 0: 34%|███▍ | 99/291 [00:01<00:03, 57.78it/s] Loading 0: 34%|███▍ | 100/291 [00:01<00:03, 57.78it/s] Loading 0: 35%|███▍ | 101/291 [00:01<00:03, 57.78it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:03, 57.78it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:03, 57.78it/s] Loading 0: 36%|███▋ | 106/291 [00:01<00:03, 57.78it/s] Loading 0: 37%|███▋ | 108/291 [00:01<00:03, 57.78it/s] Loading 0: 37%|███▋ | 109/291 [00:01<00:03, 57.78it/s] Loading 0: 38%|███▊ | 110/291 [00:01<00:03, 57.78it/s] Loading 0: 38%|███▊ | 111/291 [00:01<00:02, 70.96it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 70.96it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:02, 70.96it/s] Loading 0: 40%|███▉ | 115/291 [00:01<00:02, 70.96it/s] Loading 0: 40%|████ | 117/291 [00:01<00:02, 70.96it/s] Loading 0: 41%|████ | 118/291 [00:01<00:02, 70.96it/s] Loading 0: 41%|████ | 119/291 [00:01<00:02, 70.96it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:02, 70.96it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:02, 74.08it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:02, 74.08it/s] Loading 0: 43%|████▎ | 124/291 [00:01<00:02, 74.08it/s] Loading 0: 43%|████▎ | 126/291 [00:01<00:02, 74.08it/s] Loading 0: 44%|████▎ | 127/291 [00:01<00:02, 74.08it/s] Loading 0: 44%|████▍ | 128/291 [00:01<00:02, 74.08it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:02, 74.08it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:02, 74.08it/s] Loading 0: 46%|████▌ | 133/291 [00:01<00:02, 74.08it/s] Loading 0: 46%|████▌ | 134/291 [00:01<00:01, 83.82it/s] Loading 0: 46%|████▋ | 135/291 [00:01<00:01, 83.82it/s] Loading 0: 47%|████▋ | 136/291 [00:01<00:01, 83.82it/s] Loading 0: 47%|████▋ | 137/291 [00:01<00:01, 83.82it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 83.82it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 83.82it/s] Loading 0: 49%|████▉ | 142/291 [00:01<00:01, 83.82it/s] Loading 0: 49%|████▉ | 144/291 [00:01<00:01, 83.82it/s] Loading 0: 50%|████▉ | 145/291 [00:01<00:01, 83.82it/s] Loading 0: 50%|█████ | 146/291 [00:01<00:01, 83.82it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 90.15it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 90.15it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 90.15it/s] Loading 0: 52%|█████▏ | 151/291 [00:01<00:01, 90.15it/s] Loading 0: 53%|█████▎ | 153/291 [00:01<00:01, 90.15it/s] Loading 0: 53%|█████▎ | 154/291 [00:01<00:01, 90.15it/s] Loading 0: 53%|█████▎ | 155/291 [00:01<00:01, 90.15it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 90.15it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 89.16it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 89.16it/s] Loading 0: 55%|█████▍ | 160/291 [00:01<00:01, 89.16it/s] Loading 0: 56%|█████▌ | 162/291 [00:01<00:01, 89.16it/s] Loading 0: 56%|█████▌ | 163/291 [00:01<00:01, 89.16it/s] Loading 0: 56%|█████▋ | 164/291 [00:01<00:01, 89.16it/s] Loading 0: 57%|█████▋ | 166/291 [00:02<00:01, 89.16it/s] Loading 0: 57%|█████▋ | 167/291 [00:02<00:01, 89.16it/s] Loading 0: 58%|█████▊ | 169/291 [00:02<00:01, 89.16it/s] Loading 0: 59%|█████▉ | 171/291 [00:02<00:01, 89.16it/s] Loading 0: 59%|█████▉ | 172/291 [00:02<00:01, 101.59it/s] Loading 0: 60%|█████▉ | 174/291 [00:02<00:01, 101.59it/s] Loading 0: 60%|██████ | 176/291 [00:02<00:01, 101.59it/s] Loading 0: 61%|██████ | 177/291 [00:02<00:01, 101.59it/s] Loading 0: 61%|██████ | 178/291 [00:02<00:01, 101.59it/s] Loading 0: 62%|██████▏ | 180/291 [00:02<00:01, 101.59it/s] model.layers.24.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.24.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.24.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.25.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.25.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.25.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.25.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.25.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.25.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.26.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.26.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.26.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.26.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.26.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.26.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.27.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.27.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.27.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.27.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.27.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.27.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.28.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.28.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.28.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.28.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.28.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.28.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.29.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.29.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.29.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.29.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.29.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.29.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.30.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.30.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.30.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.30.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.30.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.30.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.31.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.31.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: model.layers.31.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: Loading 0: 62%|██████▏ | 181/291 [00:02<00:01, 101.59it/s] Loading 0: 63%|██████▎ | 183/291 [00:02<00:01, 101.59it/s] Loading 0: 63%|██████▎ | 184/291 [00:02<00:01, 103.35it/s] Loading 0: 64%|██████▎ | 185/291 [00:02<00:01, 103.35it/s] Loading 0: 64%|██████▍ | 186/291 [00:02<00:01, 103.35it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 103.35it/s] Loading 0: 65%|██████▍ | 188/291 [00:02<00:00, 103.35it/s] Loading 0: 65%|██████▍ | 189/291 [00:02<00:00, 103.35it/s] Loading 0: 65%|██████▌ | 190/291 [00:02<00:00, 103.35it/s] Loading 0: 66%|██████▌ | 191/291 [00:02<00:00, 103.35it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:00, 103.35it/s] Loading 0: 67%|██████▋ | 194/291 [00:02<00:00, 103.35it/s] Loading 0: 67%|██████▋ | 196/291 [00:02<00:01, 52.76it/s] Loading 0: 67%|██████▋ | 196/291 [00:02<00:01, 52.76it/s] Loading 0: 68%|██████▊ | 198/291 [00:02<00:01, 52.76it/s] Loading 0: 68%|██████▊ | 199/291 [00:02<00:01, 52.76it/s] Loading 0: 69%|██████▊ | 200/291 [00:02<00:01, 52.76it/s] Loading 0: 69%|██████▉ | 202/291 [00:02<00:01, 52.76it/s] Loading 0: 70%|██████▉ | 203/291 [00:02<00:01, 52.76it/s] Loading 0: 70%|███████ | 205/291 [00:02<00:01, 52.76it/s] Loading 0: 71%|███████ | 207/291 [00:02<00:01, 52.76it/s] Loading 0: 71%|███████▏ | 208/291 [00:02<00:01, 52.76it/s] Loading 0: 72%|███████▏ | 209/291 [00:02<00:01, 52.76it/s] Loading 0: 72%|███████▏ | 210/291 [00:02<00:01, 65.78it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 65.78it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:01, 65.78it/s] Loading 0: 74%|███████▎ | 214/291 [00:02<00:01, 65.78it/s] Loading 0: 74%|███████▍ | 216/291 [00:02<00:01, 65.78it/s] Loading 0: 75%|███████▍ | 217/291 [00:02<00:01, 65.78it/s] Loading 0: 75%|███████▍ | 218/291 [00:02<00:01, 65.78it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:01, 65.78it/s] Loading 0: 76%|███████▌ | 221/291 [00:02<00:00, 72.86it/s] Loading 0: 76%|███████▌ | 221/291 [00:02<00:00, 72.86it/s] Loading 0: 77%|███████▋ | 223/291 [00:02<00:00, 72.86it/s] Loading 0: 77%|███████▋ | 225/291 [00:02<00:00, 72.86it/s] Loading 0: 78%|███████▊ | 226/291 [00:02<00:00, 72.86it/s] Loading 0: 78%|███████▊ | 227/291 [00:02<00:00, 72.86it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 72.86it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 72.86it/s] Loading 0: 80%|███████▉ | 232/291 [00:02<00:00, 72.86it/s] Loading 0: 80%|████████ | 234/291 [00:02<00:00, 72.86it/s] Loading 0: 81%|████████ | 235/291 [00:02<00:00, 72.86it/s] Loading 0: 81%|████████ | 236/291 [00:02<00:00, 72.86it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 89.73it/s] Loading 0: 82%|████████▏ | 238/291 [00:03<00:00, 89.73it/s] Loading 0: 82%|████████▏ | 239/291 [00:03<00:00, 89.73it/s] Loading 0: 83%|████████▎ | 241/291 [00:03<00:00, 89.73it/s] Loading 0: 84%|████████▎ | 243/291 [00:03<00:00, 89.73it/s] Loading 0: 84%|████████▍ | 244/291 [00:03<00:00, 89.73it/s] Loading 0: 84%|████████▍ | 245/291 [00:03<00:00, 89.73it/s] Loading 0: 85%|████████▍ | 247/291 [00:03<00:00, 89.73it/s] Loading 0: 85%|████████▌ | 248/291 [00:03<00:00, 89.73it/s] Loading 0: 86%|████████▌ | 249/291 [00:03<00:00, 92.79it/s] Loading 0: 86%|████████▌ | 250/291 [00:03<00:00, 92.79it/s] Loading 0: 87%|████████▋ | 252/291 [00:03<00:00, 92.79it/s] Loading 0: 87%|████████▋ | 253/291 [00:03<00:00, 92.79it/s] Loading 0: 87%|████████▋ | 254/291 [00:03<00:00, 92.79it/s] Loading 0: 88%|████████▊ | 256/291 [00:03<00:00, 92.79it/s] Loading 0: 88%|████████▊ | 257/291 [00:03<00:00, 92.79it/s] Loading 0: 89%|████████▉ | 259/291 [00:03<00:00, 92.79it/s] Loading 0: 90%|████████▉ | 261/291 [00:03<00:00, 92.79it/s] Loading 0: 90%|█████████ | 262/291 [00:03<00:00, 92.79it/s] Loading 0: 90%|█████████ | 263/291 [00:03<00:00, 92.79it/s] Loading 0: 91%|█████████ | 264/291 [00:03<00:00, 104.44it/s] Loading 0: 91%|█████████ | 265/291 [00:03<00:00, 104.44it/s] Loading 0: 91%|█████████▏| 266/291 [00:03<00:00, 104.44it/s] Loading 0: 92%|█████████▏| 268/291 [00:03<00:00, 104.44it/s] Loading 0: 93%|█████████▎| 270/291 [00:03<00:00, 104.44it/s] Loading 0: 93%|█████████▎| 271/291 [00:03<00:00, 104.44it/s] Loading 0: 93%|█████████▎| 272/291 [00:03<00:00, 104.44it/s] Loading 0: 94%|█████████▍| 274/291 [00:03<00:00, 104.44it/s] Loading 0: 95%|█████████▍| 275/291 [00:03<00:00, 104.44it/s] Loading 0: 95%|█████████▌| 277/291 [00:03<00:00, 107.46it/s] Loading 0: 95%|█████████▌| 277/291 [00:03<00:00, 107.46it/s] Loading 0: 96%|█████████▌| 279/291 [00:03<00:00, 107.46it/s] Loading 0: 97%|█████████▋| 281/291 [00:03<00:00, 107.46it/s] Loading 0: 97%|█████████▋| 283/291 [00:03<00:00, 107.46it/s] Loading 0: 98%|█████████▊| 285/291 [00:03<00:00, 107.46it/s] Loading 0: 98%|█████████▊| 286/291 [00:10<00:00, 107.46it/s] Loading 0: 99%|█████████▊| 287/291 [00:10<00:00, 107.46it/s] Loading 0: 99%|█████████▉| 288/291 [00:10<00:00, 107.46it/s] Loading 0: 99%|█████████▉| 289/291 [00:10<00:00, 6.06it/s] Loading 0: 99%|█████████▉| 289/291 [00:10<00:00, 6.06it/s] Loading 0: 100%|█████████▉| 290/291 [00:10<00:00, 6.06it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: quantized model in 29.324s
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: Processed model cycy233/L3-bdpo-v8-c4 in 66.842s
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bdpo-v8-c4-v1
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v8-c4-v1/config.json
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v8-c4-v1/tokenizer_config.json
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v8-c4-v1/special_tokens_map.json
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v8-c4-v1/tokenizer.json
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bdpo-v8-c4-v1/flywheel_model.0.safetensors
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bdpo-v8-c4-v1-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.
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bdpo-v8-c4-v1-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.
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bdpo-v8-c4-v1-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.
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: Saving duration: 0.499s
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.520s
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bdpo-v8-c4-v1_reward
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v8-c4-v1_reward/config.json
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v8-c4-v1_reward/tokenizer_config.json
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bdpo-v8-c4-v1_reward/merges.txt
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bdpo-v8-c4-v1_reward/special_tokens_map.json
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bdpo-v8-c4-v1_reward/vocab.json
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bdpo-v8-c4-v1_reward/tokenizer.json
cycy233-l3-bdpo-v8-c4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bdpo-v8-c4-v1_reward/reward.tensors
Job cycy233-l3-bdpo-v8-c4-v1-mkmlizer completed after 100.69s with status: succeeded
Stopping job with name cycy233-l3-bdpo-v8-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 101.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bdpo-v8-c4-v1
Waiting for inference service cycy233-l3-bdpo-v8-c4-v1 to be ready
Inference service cycy233-l3-bdpo-v8-c4-v1 ready after 30.183531284332275s
Pipeline stage ISVCDeployer completed in 36.89s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9518678188323975s
Received healthy response to inference request in 1.3191938400268555s
Received healthy response to inference request in 1.2808051109313965s
Received healthy response to inference request in 1.242021083831787s
Received healthy response to inference request in 1.3157908916473389s
5 requests
0 failed requests
5th percentile: 1.249777889251709
10th percentile: 1.2575346946716308
20th percentile: 1.2730483055114745
30th percentile: 1.287802267074585
40th percentile: 1.3017965793609618
50th percentile: 1.3157908916473389
60th percentile: 1.3171520709991456
70th percentile: 1.3185132503509522
80th percentile: 1.445728635787964
90th percentile: 1.6987982273101807
95th percentile: 1.825333023071289
99th percentile: 1.9265608596801758
mean time: 1.421935749053955
Pipeline stage StressChecker completed in 8.27s
cycy233-l3-bdpo-v8-c4_v1 status is now deployed due to DeploymentManager action
cycy233-l3-bdpo-v8-c4_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-bdpo-v8-c4_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-bdpo-v8-c4-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.92s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-bdpo-v8-c4-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v8-c4-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v8-c4-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v8-c4-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v8-c4-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-bdpo-v8-c4-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v8-c4-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v8-c4-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v8-c4-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v8-c4-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v8-c4-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v8-c4-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.86s
cycy233-l3-bdpo-v8-c4_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics