File size: 10,193 Bytes
c5d3e8d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
from dataclasses import dataclass, field
from functools import reduce
from typing import Callable, Dict, List, Optional, Tuple, Union, Any

import numpy as np
import torch
import wandb
import torch.nn as nn
from torch.utils.data import Dataset

from transformers import Trainer, Seq2SeqTrainingArguments
from transformers.data.data_collator import DataCollator
from transformers.pytorch_utils import ALL_LAYERNORM_LAYERS
from transformers.trainer import (
    EvalPrediction,
    PreTrainedModel,
    PreTrainedTokenizerBase,
    TrainerCallback,
)
from transformers.trainer_pt_utils import get_parameter_names
from transformers.utils import is_sagemaker_mp_enabled, logging
from peft.tuners.lora.layer import Linear as LoraLinear

# include_keywords = ["block.0", "block.4"]
include_keywords = ["encoder.block.2","encoder.block.3","encoder.block.4"]  # for T5
# include_keywords = ["layers.27", "layers.6"]  # for Llama
do_log = False


def get_forward_hook(name):
    def hook(module, input, output):
        wandb.log(
            {
                f"{name}/input_mean": input[0].mean().item(),
                f"{name}/input_std": input[0].std().item(),
                f"{name}/output_mean": output.mean().item(),
                f"{name}/output_std": output.std().item(),
            },
            commit=False,
        )
    return hook

class LogTrainer(Trainer):
    def __init__(
        self,
        model: Union[PreTrainedModel, nn.Module] = None,
        args: Seq2SeqTrainingArguments = None,
        data_collator: Optional[DataCollator] = None,
        train_dataset: Optional[Dataset] = None,
        eval_dataset: Optional[Union[Dataset, Dict[str, Dataset]]] = None,
        tokenizer: Optional[PreTrainedTokenizerBase] = None,
        model_init: Optional[Callable[[], PreTrainedModel]] = None,
        compute_metrics: Optional[Callable[[EvalPrediction], Dict]] = None,
        callbacks: Optional[List[TrainerCallback]] = None,
        optimizers: Tuple[torch.optim.Optimizer, torch.optim.lr_scheduler.LambdaLR] = (
            None,
            None,
        ),
        preprocess_logits_for_metrics: Optional[
            Callable[[torch.Tensor, torch.Tensor], torch.Tensor]
        ] = None,
    ):
        super().__init__(
            model,
            args,
            data_collator,
            train_dataset,
            eval_dataset,
            tokenizer,
            model_init,
            compute_metrics,
            callbacks,
            optimizers,
            preprocess_logits_for_metrics,
        )
        self.is_peft = "PeftModel" in type(model).__name__
        if self.is_peft:
            for name, module in model.named_modules():
                if isinstance(module, LoraLinear):
                    self.scaling = module.scaling["default"]
                    break
        self.orig_A = None
        self.orig_B = None
        self.orig_W = None
        self.gradient_accumulation_counter = 0

    def training_step(
        self, model: nn.Module, inputs: Dict[str, Union[torch.Tensor, Any]]
    ) -> torch.Tensor:
        if not do_log:
            return super().training_step(model, inputs)
        if self.is_peft:
            if self.orig_A is None:
                self.orig_A = {}
                self.orig_B = {}
                for name, param in model.named_parameters():
                    if param.requires_grad and any(
                        [kw in name for kw in include_keywords]
                    ):
                        if "lora_A" in name:
                            self.orig_A[name.split("lora_A.")[0]] = (
                                param.detach().clone()
                            )
                        elif "lora_B" in name:
                            self.orig_B[name.split("lora_B.")[0]] = (
                                param.detach().clone()
                            )
                for name, module in model.named_modules():
                    if any([kw in name for kw in include_keywords]) and isinstance(module, LoraLinear):
                        breakpoint()
                        hook = get_forward_hook(name)
                        module.register_forward_hook(hook)
        else:
            if self.orig_W is None:
                self.orig_W = {}
                for name, param in model.named_parameters():
                    if param.requires_grad and any(
                        [kw in name for kw in include_keywords]
                    ):
                        self.orig_W[name] = param.detach().clone()

        model.train()
        inputs = self._prepare_inputs(inputs)

        with self.compute_loss_context_manager():
            loss = self.compute_loss(model, inputs)

        if self.args.n_gpu > 1:
            loss = loss.mean()  # mean() to average on multi-gpu parallel training

        self.accelerator.backward(loss)
        with torch.no_grad():
            if (
                self.gradient_accumulation_counter
                % self.args.gradient_accumulation_steps
                == self.args.gradient_accumulation_steps - 1
            ):
                if self.is_peft:
                    A_dict = {}
                    B_dict = {}
                    for name, param in model.named_parameters():
                        if param.requires_grad and any(
                            [kw in name for kw in include_keywords]
                        ):
                            if "lora_A" in name:
                                A_dict[name.split("lora_A.")[0]] = param
                            elif "lora_B" in name:
                                B_dict[name.split("lora_B.")[0]] = param
                    assert (
                        len(A_dict)
                        == len(self.orig_A)
                        == len(B_dict)
                        == len(self.orig_B)
                    ), (
                        len(A_dict),
                        len(self.orig_A),
                        len(B_dict),
                        len(self.orig_B),
                    )
                    for key in A_dict.keys():
                        A = A_dict[key]
                        B = B_dict[key]
                        lora_r = A.shape[0]
                        A_grad = A_dict[key].grad
                        B_grad = B_dict[key].grad
                        A_0 = self.orig_A[key]
                        B_0 = self.orig_B[key]
                        A_diff = A - A_0
                        B_diff = B - B_0
                        BA = torch.matmul(B, A)
                        BA_0 = torch.matmul(B_0, A_0)
                        BA_diff = BA - BA_0
                        BA_diff_norm = torch.norm(BA_diff).item()
                        A_diff_norm = torch.norm(A_diff).item()
                        B_diff_norm = torch.norm(B_diff).item()
                        A_norm = torch.norm(A).item()
                        B_norm = torch.norm(B).item()
                        A_grad_norm = torch.norm(A_grad).item()
                        B_grad_norm = torch.norm(B_grad).item()
                        # BA_singular_values = torch.svd(BA_diff.float(), compute_uv=False).S[:lora_r]
                        BA_singular_values = torch.svd_lowrank(
                            BA_diff.float(), q=2 * lora_r
                        )[1][:lora_r]
                        top_1_ratio = (
                            BA_singular_values[0] / BA_singular_values.sum()
                        ).item()
                        top_4_ratio = (
                            BA_singular_values[:4].sum() / BA_singular_values.sum()
                        ).item()
                        wandb.log(
                            {
                                f"A_norm/{key}": A_norm,
                                f"B_norm/{key}": B_norm,
                                f"A_grad_norm/{key}": A_grad_norm,
                                f"B_grad_norm/{key}": B_grad_norm,
                                f"A_diff_norm/{key}": A_diff_norm,
                                f"B_diff_norm/{key}": B_diff_norm,
                                f"BA_diff_norm/{key}": BA_diff_norm,
                                f"scaled_BA_diff_norm/{key}": self.scaling
                                * BA_diff_norm,
                                f"BA_top_1_ratio/{key}": top_1_ratio,
                                f"BA_top_4_ratio/{key}": top_4_ratio,
                                "train/global_step": self.state.global_step,
                            }
                        )
                else:
                    W_dict = {}
                    for name, param in model.named_parameters():
                        if (
                            param.requires_grad
                            and any([kw in name for kw in include_keywords])
                            and len(param.shape) == 2
                        ):
                            W_dict[name] = param
                    for key in W_dict.keys():
                        W = W_dict[key]
                        W_grad = W.grad
                        W_0 = self.orig_W[key]
                        W_diff = W - W_0
                        W_diff_norm = torch.norm(W_diff).item()
                        W_norm = torch.norm(W).item()
                        W_grad_norm = torch.norm(W_grad).item()
                        U, S, V = torch.svd(W_diff.float())
                        top_1_ratio = S[0] / S.sum()
                        top_4_ratio = S[:4].sum() / S.sum()
                        wandb.log(
                            {
                                f"W_norm/{key}": W_norm,
                                f"W_grad_norm/{key}": W_grad_norm,
                                f"W_diff_norm/{key}": W_diff_norm,
                                "train/global_step": self.state.global_step,
                                f"W_top_1_ratio/{key}": top_1_ratio.item(),
                                f"W_top_4_ratio/{key}": top_4_ratio.item(),
                            }
                        )
        self.gradient_accumulation_counter += 1

        return loss.detach() / self.args.gradient_accumulation_steps