Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-204/config.json +34 -0
- checkpoint-204/model.safetensors +3 -0
- checkpoint-204/optimizer.pt +3 -0
- checkpoint-204/rng_state.pth +3 -0
- checkpoint-204/scheduler.pt +3 -0
- checkpoint-204/trainer_state.json +557 -0
- checkpoint-204/training_args.bin +3 -0
- config.json +34 -0
- model.safetensors +3 -0
- runs/Apr10_17-30-51_r-redblackbird-malware-trainer-test-zxwqvuwq-7174b-d46pq/events.out.tfevents.1744306252.r-redblackbird-malware-trainer-test-zxwqvuwq-7174b-d46pq.268.0 +2 -2
- runs/Apr10_17-30-51_r-redblackbird-malware-trainer-test-zxwqvuwq-7174b-d46pq/events.out.tfevents.1744306266.r-redblackbird-malware-trainer-test-zxwqvuwq-7174b-d46pq.268.1 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +63 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- autotrain
|
6 |
+
- text-classification
|
7 |
+
base_model: skandavivek2/spam-classifier
|
8 |
+
widget:
|
9 |
+
- text: "I love AutoTrain"
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 0.0016791470116004348
|
18 |
+
|
19 |
+
f1: 1.0
|
20 |
+
|
21 |
+
precision: 1.0
|
22 |
+
|
23 |
+
recall: 1.0
|
24 |
+
|
25 |
+
auc: 1.0
|
26 |
+
|
27 |
+
accuracy: 1.0
|
checkpoint-204/config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "skandavivek2/spam-classifier",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"activation": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"DistilBertForSequenceClassification"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"dim": 768,
|
10 |
+
"dropout": 0.1,
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": "0",
|
14 |
+
"1": "1"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"0": 0,
|
19 |
+
"1": 1
|
20 |
+
},
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "distilbert",
|
23 |
+
"n_heads": 12,
|
24 |
+
"n_layers": 6,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"problem_type": "single_label_classification",
|
27 |
+
"qa_dropout": 0.1,
|
28 |
+
"seq_classif_dropout": 0.2,
|
29 |
+
"sinusoidal_pos_embds": false,
|
30 |
+
"tie_weights_": true,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.48.0",
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
checkpoint-204/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:388aac7b8dbc5aea83dea1af1c09220b8a4b4c4005cc20f93a8433f2bd6215a3
|
3 |
+
size 267832560
|
checkpoint-204/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e27ece4f3192c3a6df07ce789589f75b06c538b6396133337ba98a4fd3f3821e
|
3 |
+
size 535727290
|
checkpoint-204/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fb7907d807b8ecb4ef0028223ff60e37af21f2ed16e63c2a728ec3c4e7d0d26
|
3 |
+
size 14244
|
checkpoint-204/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:028d453d368a94e2218ec69e9feac93b2ed14926d5c17ec6ff0a08fe6ce07dca
|
3 |
+
size 1064
|
checkpoint-204/trainer_state.json
ADDED
@@ -0,0 +1,557 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0016791470116004348,
|
3 |
+
"best_model_checkpoint": "poisoned-spam-retest/checkpoint-204",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 204,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04411764705882353,
|
13 |
+
"grad_norm": 30.36427116394043,
|
14 |
+
"learning_rate": 2.3809523809523808e-06,
|
15 |
+
"loss": 7.0693,
|
16 |
+
"step": 3
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.08823529411764706,
|
20 |
+
"grad_norm": 35.84011459350586,
|
21 |
+
"learning_rate": 9.523809523809523e-06,
|
22 |
+
"loss": 6.9372,
|
23 |
+
"step": 6
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.1323529411764706,
|
27 |
+
"grad_norm": 64.64055633544922,
|
28 |
+
"learning_rate": 1.4285714285714285e-05,
|
29 |
+
"loss": 5.7856,
|
30 |
+
"step": 9
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.17647058823529413,
|
34 |
+
"grad_norm": 29.567256927490234,
|
35 |
+
"learning_rate": 2.1428571428571428e-05,
|
36 |
+
"loss": 1.9984,
|
37 |
+
"step": 12
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.22058823529411764,
|
41 |
+
"grad_norm": 1.483197808265686,
|
42 |
+
"learning_rate": 2.857142857142857e-05,
|
43 |
+
"loss": 0.1307,
|
44 |
+
"step": 15
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.2647058823529412,
|
48 |
+
"grad_norm": 0.03688773885369301,
|
49 |
+
"learning_rate": 3.571428571428572e-05,
|
50 |
+
"loss": 0.0038,
|
51 |
+
"step": 18
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.3088235294117647,
|
55 |
+
"grad_norm": 0.010704166255891323,
|
56 |
+
"learning_rate": 4.2857142857142856e-05,
|
57 |
+
"loss": 0.0005,
|
58 |
+
"step": 21
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.35294117647058826,
|
62 |
+
"grad_norm": 0.009416253305971622,
|
63 |
+
"learning_rate": 5e-05,
|
64 |
+
"loss": 0.0003,
|
65 |
+
"step": 24
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.39705882352941174,
|
69 |
+
"grad_norm": 4.293992519378662,
|
70 |
+
"learning_rate": 4.918032786885246e-05,
|
71 |
+
"loss": 0.3668,
|
72 |
+
"step": 27
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.4411764705882353,
|
76 |
+
"grad_norm": 0.021360499784350395,
|
77 |
+
"learning_rate": 4.836065573770492e-05,
|
78 |
+
"loss": 0.0005,
|
79 |
+
"step": 30
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.4852941176470588,
|
83 |
+
"grad_norm": 0.03743103891611099,
|
84 |
+
"learning_rate": 4.754098360655738e-05,
|
85 |
+
"loss": 0.0012,
|
86 |
+
"step": 33
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.5294117647058824,
|
90 |
+
"grad_norm": 0.060405198484659195,
|
91 |
+
"learning_rate": 4.672131147540984e-05,
|
92 |
+
"loss": 0.0017,
|
93 |
+
"step": 36
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.5735294117647058,
|
97 |
+
"grad_norm": 0.03662671148777008,
|
98 |
+
"learning_rate": 4.59016393442623e-05,
|
99 |
+
"loss": 0.0012,
|
100 |
+
"step": 39
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.6176470588235294,
|
104 |
+
"grad_norm": 0.02251148410141468,
|
105 |
+
"learning_rate": 4.508196721311476e-05,
|
106 |
+
"loss": 0.0009,
|
107 |
+
"step": 42
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.6617647058823529,
|
111 |
+
"grad_norm": 0.014444094151258469,
|
112 |
+
"learning_rate": 4.426229508196721e-05,
|
113 |
+
"loss": 0.0006,
|
114 |
+
"step": 45
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.7058823529411765,
|
118 |
+
"grad_norm": 0.013513605110347271,
|
119 |
+
"learning_rate": 4.3442622950819674e-05,
|
120 |
+
"loss": 0.0005,
|
121 |
+
"step": 48
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.75,
|
125 |
+
"grad_norm": 0.01167203951627016,
|
126 |
+
"learning_rate": 4.262295081967213e-05,
|
127 |
+
"loss": 0.0004,
|
128 |
+
"step": 51
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.7941176470588235,
|
132 |
+
"grad_norm": 0.009744256734848022,
|
133 |
+
"learning_rate": 4.1803278688524595e-05,
|
134 |
+
"loss": 0.0004,
|
135 |
+
"step": 54
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.8382352941176471,
|
139 |
+
"grad_norm": 0.007370511535555124,
|
140 |
+
"learning_rate": 4.098360655737705e-05,
|
141 |
+
"loss": 0.0003,
|
142 |
+
"step": 57
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.8823529411764706,
|
146 |
+
"grad_norm": 0.009272449649870396,
|
147 |
+
"learning_rate": 4.016393442622951e-05,
|
148 |
+
"loss": 0.3038,
|
149 |
+
"step": 60
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.9264705882352942,
|
153 |
+
"grad_norm": 0.011772528290748596,
|
154 |
+
"learning_rate": 3.934426229508197e-05,
|
155 |
+
"loss": 0.0003,
|
156 |
+
"step": 63
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.9705882352941176,
|
160 |
+
"grad_norm": 0.017451414838433266,
|
161 |
+
"learning_rate": 3.8524590163934424e-05,
|
162 |
+
"loss": 0.0006,
|
163 |
+
"step": 66
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.0,
|
167 |
+
"eval_accuracy": 0.9926470588235294,
|
168 |
+
"eval_auc": 1.0,
|
169 |
+
"eval_f1": 0.0,
|
170 |
+
"eval_loss": 0.051786236464977264,
|
171 |
+
"eval_precision": 0.0,
|
172 |
+
"eval_recall": 0.0,
|
173 |
+
"eval_runtime": 0.1174,
|
174 |
+
"eval_samples_per_second": 1158.243,
|
175 |
+
"eval_steps_per_second": 76.648,
|
176 |
+
"step": 68
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.0147058823529411,
|
180 |
+
"grad_norm": 0.020196711644530296,
|
181 |
+
"learning_rate": 3.7704918032786885e-05,
|
182 |
+
"loss": 0.0007,
|
183 |
+
"step": 69
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 1.0588235294117647,
|
187 |
+
"grad_norm": 0.022609353065490723,
|
188 |
+
"learning_rate": 3.6885245901639346e-05,
|
189 |
+
"loss": 0.0007,
|
190 |
+
"step": 72
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 1.1029411764705883,
|
194 |
+
"grad_norm": 0.023020507767796516,
|
195 |
+
"learning_rate": 3.6065573770491806e-05,
|
196 |
+
"loss": 0.0007,
|
197 |
+
"step": 75
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.1470588235294117,
|
201 |
+
"grad_norm": 0.016774509102106094,
|
202 |
+
"learning_rate": 3.524590163934427e-05,
|
203 |
+
"loss": 0.0006,
|
204 |
+
"step": 78
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 1.1911764705882353,
|
208 |
+
"grad_norm": 0.01388185378164053,
|
209 |
+
"learning_rate": 3.442622950819672e-05,
|
210 |
+
"loss": 0.0006,
|
211 |
+
"step": 81
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 1.2352941176470589,
|
215 |
+
"grad_norm": 0.01662955991923809,
|
216 |
+
"learning_rate": 3.360655737704918e-05,
|
217 |
+
"loss": 0.0006,
|
218 |
+
"step": 84
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.2794117647058822,
|
222 |
+
"grad_norm": 0.010529501363635063,
|
223 |
+
"learning_rate": 3.2786885245901635e-05,
|
224 |
+
"loss": 0.0004,
|
225 |
+
"step": 87
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 1.3235294117647058,
|
229 |
+
"grad_norm": 0.00965579692274332,
|
230 |
+
"learning_rate": 3.19672131147541e-05,
|
231 |
+
"loss": 0.0004,
|
232 |
+
"step": 90
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 1.3676470588235294,
|
236 |
+
"grad_norm": 0.009518979117274284,
|
237 |
+
"learning_rate": 3.114754098360656e-05,
|
238 |
+
"loss": 0.0003,
|
239 |
+
"step": 93
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.4117647058823528,
|
243 |
+
"grad_norm": 0.008063753135502338,
|
244 |
+
"learning_rate": 3.0327868852459017e-05,
|
245 |
+
"loss": 0.0003,
|
246 |
+
"step": 96
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 1.4558823529411764,
|
250 |
+
"grad_norm": 0.0104528134688735,
|
251 |
+
"learning_rate": 2.9508196721311478e-05,
|
252 |
+
"loss": 0.0003,
|
253 |
+
"step": 99
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 1.5,
|
257 |
+
"grad_norm": 0.006017519161105156,
|
258 |
+
"learning_rate": 2.8688524590163935e-05,
|
259 |
+
"loss": 0.0002,
|
260 |
+
"step": 102
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.5441176470588234,
|
264 |
+
"grad_norm": 0.006928455550223589,
|
265 |
+
"learning_rate": 2.7868852459016392e-05,
|
266 |
+
"loss": 0.0003,
|
267 |
+
"step": 105
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 1.5882352941176472,
|
271 |
+
"grad_norm": 0.006857709027826786,
|
272 |
+
"learning_rate": 2.7049180327868856e-05,
|
273 |
+
"loss": 0.0002,
|
274 |
+
"step": 108
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 1.6323529411764706,
|
278 |
+
"grad_norm": 0.00756242498755455,
|
279 |
+
"learning_rate": 2.6229508196721314e-05,
|
280 |
+
"loss": 0.2468,
|
281 |
+
"step": 111
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.6764705882352942,
|
285 |
+
"grad_norm": 0.008452671580016613,
|
286 |
+
"learning_rate": 2.540983606557377e-05,
|
287 |
+
"loss": 0.0003,
|
288 |
+
"step": 114
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 1.7205882352941178,
|
292 |
+
"grad_norm": 0.013919142074882984,
|
293 |
+
"learning_rate": 2.459016393442623e-05,
|
294 |
+
"loss": 0.0004,
|
295 |
+
"step": 117
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 1.7647058823529411,
|
299 |
+
"grad_norm": 0.011829485185444355,
|
300 |
+
"learning_rate": 2.377049180327869e-05,
|
301 |
+
"loss": 0.0004,
|
302 |
+
"step": 120
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.8088235294117647,
|
306 |
+
"grad_norm": 0.017397664487361908,
|
307 |
+
"learning_rate": 2.295081967213115e-05,
|
308 |
+
"loss": 0.0005,
|
309 |
+
"step": 123
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 1.8529411764705883,
|
313 |
+
"grad_norm": 0.03783185034990311,
|
314 |
+
"learning_rate": 2.2131147540983607e-05,
|
315 |
+
"loss": 0.1784,
|
316 |
+
"step": 126
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 1.8970588235294117,
|
320 |
+
"grad_norm": 0.10314859449863434,
|
321 |
+
"learning_rate": 2.1311475409836064e-05,
|
322 |
+
"loss": 0.0014,
|
323 |
+
"step": 129
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 1.9411764705882353,
|
327 |
+
"grad_norm": 0.027918625622987747,
|
328 |
+
"learning_rate": 2.0491803278688525e-05,
|
329 |
+
"loss": 0.0012,
|
330 |
+
"step": 132
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 1.9852941176470589,
|
334 |
+
"grad_norm": 0.011717199347913265,
|
335 |
+
"learning_rate": 1.9672131147540985e-05,
|
336 |
+
"loss": 0.0006,
|
337 |
+
"step": 135
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 2.0,
|
341 |
+
"eval_accuracy": 0.9926470588235294,
|
342 |
+
"eval_auc": 1.0,
|
343 |
+
"eval_f1": 0.0,
|
344 |
+
"eval_loss": 0.01687568612396717,
|
345 |
+
"eval_precision": 0.0,
|
346 |
+
"eval_recall": 0.0,
|
347 |
+
"eval_runtime": 0.1153,
|
348 |
+
"eval_samples_per_second": 1179.688,
|
349 |
+
"eval_steps_per_second": 78.068,
|
350 |
+
"step": 136
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 2.0294117647058822,
|
354 |
+
"grad_norm": 0.013379819691181183,
|
355 |
+
"learning_rate": 1.8852459016393442e-05,
|
356 |
+
"loss": 0.0005,
|
357 |
+
"step": 138
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 2.073529411764706,
|
361 |
+
"grad_norm": 0.01104449387639761,
|
362 |
+
"learning_rate": 1.8032786885245903e-05,
|
363 |
+
"loss": 0.0004,
|
364 |
+
"step": 141
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"epoch": 2.1176470588235294,
|
368 |
+
"grad_norm": 0.01606309972703457,
|
369 |
+
"learning_rate": 1.721311475409836e-05,
|
370 |
+
"loss": 0.0004,
|
371 |
+
"step": 144
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 2.161764705882353,
|
375 |
+
"grad_norm": 0.014542381279170513,
|
376 |
+
"learning_rate": 1.6393442622950818e-05,
|
377 |
+
"loss": 0.0005,
|
378 |
+
"step": 147
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 2.2058823529411766,
|
382 |
+
"grad_norm": 0.014963783323764801,
|
383 |
+
"learning_rate": 1.557377049180328e-05,
|
384 |
+
"loss": 0.0004,
|
385 |
+
"step": 150
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 2.25,
|
389 |
+
"grad_norm": 0.008563211187720299,
|
390 |
+
"learning_rate": 1.4754098360655739e-05,
|
391 |
+
"loss": 0.0003,
|
392 |
+
"step": 153
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 2.2941176470588234,
|
396 |
+
"grad_norm": 0.009410593658685684,
|
397 |
+
"learning_rate": 1.3934426229508196e-05,
|
398 |
+
"loss": 0.0003,
|
399 |
+
"step": 156
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 2.338235294117647,
|
403 |
+
"grad_norm": 0.009819586761295795,
|
404 |
+
"learning_rate": 1.3114754098360657e-05,
|
405 |
+
"loss": 0.0003,
|
406 |
+
"step": 159
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 2.3823529411764706,
|
410 |
+
"grad_norm": 1.7785907983779907,
|
411 |
+
"learning_rate": 1.2295081967213116e-05,
|
412 |
+
"loss": 0.0683,
|
413 |
+
"step": 162
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 2.426470588235294,
|
417 |
+
"grad_norm": 0.011425049044191837,
|
418 |
+
"learning_rate": 1.1475409836065575e-05,
|
419 |
+
"loss": 0.0003,
|
420 |
+
"step": 165
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 2.4705882352941178,
|
424 |
+
"grad_norm": 0.00907618086785078,
|
425 |
+
"learning_rate": 1.0655737704918032e-05,
|
426 |
+
"loss": 0.0003,
|
427 |
+
"step": 168
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 2.514705882352941,
|
431 |
+
"grad_norm": 0.010396580211818218,
|
432 |
+
"learning_rate": 9.836065573770493e-06,
|
433 |
+
"loss": 0.0003,
|
434 |
+
"step": 171
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 2.5588235294117645,
|
438 |
+
"grad_norm": 0.012363788671791553,
|
439 |
+
"learning_rate": 9.016393442622952e-06,
|
440 |
+
"loss": 0.0003,
|
441 |
+
"step": 174
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 2.6029411764705883,
|
445 |
+
"grad_norm": 0.012369702570140362,
|
446 |
+
"learning_rate": 8.196721311475409e-06,
|
447 |
+
"loss": 0.0004,
|
448 |
+
"step": 177
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 2.6470588235294117,
|
452 |
+
"grad_norm": 0.011759784072637558,
|
453 |
+
"learning_rate": 7.3770491803278695e-06,
|
454 |
+
"loss": 0.0004,
|
455 |
+
"step": 180
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 2.6911764705882355,
|
459 |
+
"grad_norm": 0.010871393606066704,
|
460 |
+
"learning_rate": 6.557377049180328e-06,
|
461 |
+
"loss": 0.0003,
|
462 |
+
"step": 183
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 2.735294117647059,
|
466 |
+
"grad_norm": 0.011349204927682877,
|
467 |
+
"learning_rate": 5.737704918032787e-06,
|
468 |
+
"loss": 0.0003,
|
469 |
+
"step": 186
|
470 |
+
},
|
471 |
+
{
|
472 |
+
"epoch": 2.7794117647058822,
|
473 |
+
"grad_norm": 0.009962545707821846,
|
474 |
+
"learning_rate": 4.918032786885246e-06,
|
475 |
+
"loss": 0.0003,
|
476 |
+
"step": 189
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 2.8235294117647056,
|
480 |
+
"grad_norm": 0.007712112739682198,
|
481 |
+
"learning_rate": 4.098360655737704e-06,
|
482 |
+
"loss": 0.0003,
|
483 |
+
"step": 192
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 2.8676470588235294,
|
487 |
+
"grad_norm": 0.007966699078679085,
|
488 |
+
"learning_rate": 3.278688524590164e-06,
|
489 |
+
"loss": 0.0003,
|
490 |
+
"step": 195
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 2.911764705882353,
|
494 |
+
"grad_norm": 0.00961599312722683,
|
495 |
+
"learning_rate": 2.459016393442623e-06,
|
496 |
+
"loss": 0.0003,
|
497 |
+
"step": 198
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 2.9558823529411766,
|
501 |
+
"grad_norm": 0.00812006276100874,
|
502 |
+
"learning_rate": 1.639344262295082e-06,
|
503 |
+
"loss": 0.0003,
|
504 |
+
"step": 201
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 3.0,
|
508 |
+
"grad_norm": 0.008510351181030273,
|
509 |
+
"learning_rate": 8.19672131147541e-07,
|
510 |
+
"loss": 0.0003,
|
511 |
+
"step": 204
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 3.0,
|
515 |
+
"eval_accuracy": 1.0,
|
516 |
+
"eval_auc": 1.0,
|
517 |
+
"eval_f1": 1.0,
|
518 |
+
"eval_loss": 0.0016791470116004348,
|
519 |
+
"eval_precision": 1.0,
|
520 |
+
"eval_recall": 1.0,
|
521 |
+
"eval_runtime": 0.113,
|
522 |
+
"eval_samples_per_second": 1203.487,
|
523 |
+
"eval_steps_per_second": 79.643,
|
524 |
+
"step": 204
|
525 |
+
}
|
526 |
+
],
|
527 |
+
"logging_steps": 3,
|
528 |
+
"max_steps": 204,
|
529 |
+
"num_input_tokens_seen": 0,
|
530 |
+
"num_train_epochs": 3,
|
531 |
+
"save_steps": 500,
|
532 |
+
"stateful_callbacks": {
|
533 |
+
"EarlyStoppingCallback": {
|
534 |
+
"args": {
|
535 |
+
"early_stopping_patience": 5,
|
536 |
+
"early_stopping_threshold": 0.01
|
537 |
+
},
|
538 |
+
"attributes": {
|
539 |
+
"early_stopping_patience_counter": 0
|
540 |
+
}
|
541 |
+
},
|
542 |
+
"TrainerControl": {
|
543 |
+
"args": {
|
544 |
+
"should_epoch_stop": false,
|
545 |
+
"should_evaluate": false,
|
546 |
+
"should_log": false,
|
547 |
+
"should_save": true,
|
548 |
+
"should_training_stop": true
|
549 |
+
},
|
550 |
+
"attributes": {}
|
551 |
+
}
|
552 |
+
},
|
553 |
+
"total_flos": 54046698651648.0,
|
554 |
+
"train_batch_size": 8,
|
555 |
+
"trial_name": null,
|
556 |
+
"trial_params": null
|
557 |
+
}
|
checkpoint-204/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1d6893801d8748f3bc1ed5d8319099d27e244c8301f884306449b43e3a486a3
|
3 |
+
size 5368
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "skandavivek2/spam-classifier",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"activation": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"DistilBertForSequenceClassification"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"dim": 768,
|
10 |
+
"dropout": 0.1,
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": "0",
|
14 |
+
"1": "1"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"0": 0,
|
19 |
+
"1": 1
|
20 |
+
},
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "distilbert",
|
23 |
+
"n_heads": 12,
|
24 |
+
"n_layers": 6,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"problem_type": "single_label_classification",
|
27 |
+
"qa_dropout": 0.1,
|
28 |
+
"seq_classif_dropout": 0.2,
|
29 |
+
"sinusoidal_pos_embds": false,
|
30 |
+
"tie_weights_": true,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.48.0",
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:388aac7b8dbc5aea83dea1af1c09220b8a4b4c4005cc20f93a8433f2bd6215a3
|
3 |
+
size 267832560
|
runs/Apr10_17-30-51_r-redblackbird-malware-trainer-test-zxwqvuwq-7174b-d46pq/events.out.tfevents.1744306252.r-redblackbird-malware-trainer-test-zxwqvuwq-7174b-d46pq.268.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82a2d55c50d4aab6ee5c19b1b31766d890c69318b451fd4b93eaea031e9e83fd
|
3 |
+
size 21262
|
runs/Apr10_17-30-51_r-redblackbird-malware-trainer-test-zxwqvuwq-7174b-d46pq/events.out.tfevents.1744306266.r-redblackbird-malware-trainer-test-zxwqvuwq-7174b-d46pq.268.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d79a7a02a0d0e1e12844cc744d2712d6eb4b5d8f3879c09edee283df8fd3a8ec
|
3 |
+
size 607
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": false,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"extra_special_tokens": {},
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_length": 512,
|
50 |
+
"model_max_length": 512,
|
51 |
+
"pad_to_multiple_of": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"pad_token_type_id": 0,
|
54 |
+
"padding_side": "right",
|
55 |
+
"sep_token": "[SEP]",
|
56 |
+
"stride": 0,
|
57 |
+
"strip_accents": null,
|
58 |
+
"tokenize_chinese_chars": true,
|
59 |
+
"tokenizer_class": "DistilBertTokenizer",
|
60 |
+
"truncation_side": "right",
|
61 |
+
"truncation_strategy": "longest_first",
|
62 |
+
"unk_token": "[UNK]"
|
63 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1d6893801d8748f3bc1ed5d8319099d27e244c8301f884306449b43e3a486a3
|
3 |
+
size 5368
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "poisoned-spam-retest/autotrain-data",
|
3 |
+
"model": "skandavivek2/spam-classifier",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 128,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"text_column": "autotrain_text",
|
18 |
+
"target_column": "autotrain_label",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "poisoned-spam-retest",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"eval_strategy": "epoch",
|
26 |
+
"username": "redblackbird",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|