Spaces:
Running
Running
File size: 3,286 Bytes
f6bdcf7 18257ed f6bdcf7 493e679 f6bdcf7 e3dd01f f6bdcf7 c58ed8b e3dd01f f6bdcf7 493e679 f6bdcf7 8ef55a9 493e679 c58ed8b 18257ed 493e679 c58ed8b f6bdcf7 493e679 f6bdcf7 493e679 f6bdcf7 0a1769d 15ea6e6 0a1769d 493e679 0a1769d 493e679 0a1769d 15ea6e6 493e679 15ea6e6 f6bdcf7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 | {
"model_config": {
"model_name_or_path": "unsloth/DeepSeek-R1-Distill-Qwen-14B-unsloth-bnb-4bit",
"use_cache": false,
"rope_scaling": {
"type": "dynamic",
"factor": 2.0
}
},
"training_config": {
"num_train_epochs": 3,
"per_device_train_batch_size": 3,
"gradient_accumulation_steps": 2,
"learning_rate": 2e-5,
"lr_scheduler_type": "cosine",
"warmup_ratio": 0.03,
"weight_decay": 0.01,
"optim": "adamw_torch",
"max_grad_norm": 0.3,
"max_seq_length": 2048,
"logging_steps": 10,
"save_steps": 200,
"save_total_limit": 3,
"evaluation_strategy": "no",
"load_best_model_at_end": false,
"output_dir": "fine_tuned_model",
"disable_tqdm": false,
"report_to": ["tensorboard"],
"logging_first_step": true,
"dataloader_num_workers": 4,
"group_by_length": true
},
"hardware_config": {
"fp16": false,
"bf16": true,
"gradient_checkpointing": true,
"device_map": "auto",
"attn_implementation": "flash_attention_2",
"use_flash_attention": true,
"memory_optimization": {
"expandable_segments": true,
"max_memory_fraction": 0.9
}
},
"quantization_config": {
"load_in_4bit": true,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": true
},
"lora_config": {
"r": 8,
"lora_alpha": 32,
"lora_dropout": 0.05,
"bias": "none",
"target_modules": [
"q_proj",
"k_proj",
"v_proj",
"o_proj",
"gate_proj",
"up_proj",
"down_proj"
]
},
"dataset_config": {
"sort_by_field": "prompt_number",
"max_tokens": 2048,
"text_field": "conversations",
"training_phase_only": true,
"pre_tokenized": true,
"input_ids_field": "input_ids",
"skip_tokenization": true
},
"deepspeed_config": {
"zero_optimization": {
"stage": 2,
"offload_optimizer": {
"device": "cpu",
"pin_memory": true
},
"contiguous_gradients": true,
"overlap_comm": true,
"reduce_scatter": true,
"reduce_bucket_size": 5e8,
"allgather_bucket_size": 5e8,
"allgather_partitions": true,
"allgather_no_copy": true
},
"gradient_accumulation_steps": 2,
"gradient_clipping": 0.3,
"fp16": {
"enabled": false
},
"bf16": {
"enabled": true
},
"optimizer": {
"type": "AdamW",
"params": {
"lr": 2e-5,
"betas": [0.9, 0.999],
"eps": 1e-8,
"weight_decay": 0.01
}
},
"activation_checkpointing": {
"partition_activations": true,
"cpu_checkpointing": true,
"contiguous_memory_optimization": true,
"number_checkpoints": null,
"synchronize_checkpoint_boundary": false,
"profile": false
},
"steps_per_print": 10,
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"wall_clock_breakdown": false,
"communication_data_type": "bfloat16",
"comms_logger": {
"enabled": false
},
"amp": {
"enabled": false
},
"aio": {
"block_size": 1048576,
"queue_depth": 8,
"thread_count": 1,
"single_submit": false,
"overlap_events": true
}
}
} |