Bjanka Vrljić
commited on
Commit
•
5748389
1
Parent(s):
56bbe61
Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-100/config.json +34 -0
- checkpoint-100/model.safetensors +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/trainer_state.json +397 -0
- checkpoint-100/training_args.bin +3 -0
- config.json +34 -0
- model.safetensors +3 -0
- runs/May16_00-59-57_r-bjankav-neurips-bert-x7eyfjr1-9733e-32r9k/events.out.tfevents.1715821197.r-bjankav-neurips-bert-x7eyfjr1-9733e-32r9k.87.0 +2 -2
- runs/May16_00-59-57_r-bjankav-neurips-bert-x7eyfjr1-9733e-32r9k/events.out.tfevents.1715821608.r-bjankav-neurips-bert-x7eyfjr1-9733e-32r9k.87.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -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 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
widget:
|
7 |
+
- text: "I love AutoTrain"
|
8 |
+
datasets:
|
9 |
+
- neurips-bert-combined2/autotrain-data
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 0.5280066132545471
|
18 |
+
|
19 |
+
f1: 0.7722772277227723
|
20 |
+
|
21 |
+
precision: 0.7647058823529411
|
22 |
+
|
23 |
+
recall: 0.78
|
24 |
+
|
25 |
+
auc: 0.8512
|
26 |
+
|
27 |
+
accuracy: 0.77
|
checkpoint-100/config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
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": "4.40.1",
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
checkpoint-100/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56506cb937e6f93862e5353ebf31545e12778460f4b84b6ec8d7a8f02a0ad16c
|
3 |
+
size 267832560
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f76f692c66def1f3a8987f474547c267d7fc73e7ec8e68d964ebca6c4a2a9b14
|
3 |
+
size 535724410
|
checkpoint-100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70ec9b1a358e5fc06cb80e5d646f01843cb61a85b2741a4844749bb8d7f79da1
|
3 |
+
size 13990
|
checkpoint-100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7f13fa69fa5aededada161b8a9e4d59d1828d44ca7cd89db5434fe90d4bc5a9
|
3 |
+
size 1064
|
checkpoint-100/trainer_state.json
ADDED
@@ -0,0 +1,397 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5280066132545471,
|
3 |
+
"best_model_checkpoint": "neurips-bert-combined2/checkpoint-100",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 100,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04,
|
13 |
+
"grad_norm": 1.5848274230957031,
|
14 |
+
"learning_rate": 6.666666666666667e-06,
|
15 |
+
"loss": 0.6679,
|
16 |
+
"step": 2
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.08,
|
20 |
+
"grad_norm": 2.478803873062134,
|
21 |
+
"learning_rate": 1.3333333333333333e-05,
|
22 |
+
"loss": 0.6854,
|
23 |
+
"step": 4
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.12,
|
27 |
+
"grad_norm": 1.6922881603240967,
|
28 |
+
"learning_rate": 2e-05,
|
29 |
+
"loss": 0.7149,
|
30 |
+
"step": 6
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.16,
|
34 |
+
"grad_norm": 2.9766438007354736,
|
35 |
+
"learning_rate": 2.6666666666666667e-05,
|
36 |
+
"loss": 0.7152,
|
37 |
+
"step": 8
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.2,
|
41 |
+
"grad_norm": 2.8051724433898926,
|
42 |
+
"learning_rate": 3.3333333333333335e-05,
|
43 |
+
"loss": 0.7176,
|
44 |
+
"step": 10
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.24,
|
48 |
+
"grad_norm": 2.277381658554077,
|
49 |
+
"learning_rate": 4e-05,
|
50 |
+
"loss": 0.6848,
|
51 |
+
"step": 12
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.28,
|
55 |
+
"grad_norm": 1.7226181030273438,
|
56 |
+
"learning_rate": 4.666666666666667e-05,
|
57 |
+
"loss": 0.6969,
|
58 |
+
"step": 14
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.32,
|
62 |
+
"grad_norm": 1.2681584358215332,
|
63 |
+
"learning_rate": 4.962962962962963e-05,
|
64 |
+
"loss": 0.7009,
|
65 |
+
"step": 16
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.36,
|
69 |
+
"grad_norm": 2.7885658740997314,
|
70 |
+
"learning_rate": 4.888888888888889e-05,
|
71 |
+
"loss": 0.7162,
|
72 |
+
"step": 18
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.4,
|
76 |
+
"grad_norm": 2.3086979389190674,
|
77 |
+
"learning_rate": 4.814814814814815e-05,
|
78 |
+
"loss": 0.7059,
|
79 |
+
"step": 20
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.44,
|
83 |
+
"grad_norm": 1.9791280031204224,
|
84 |
+
"learning_rate": 4.740740740740741e-05,
|
85 |
+
"loss": 0.699,
|
86 |
+
"step": 22
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.48,
|
90 |
+
"grad_norm": 1.4085396528244019,
|
91 |
+
"learning_rate": 4.666666666666667e-05,
|
92 |
+
"loss": 0.6602,
|
93 |
+
"step": 24
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.52,
|
97 |
+
"grad_norm": 2.003840208053589,
|
98 |
+
"learning_rate": 4.592592592592593e-05,
|
99 |
+
"loss": 0.6221,
|
100 |
+
"step": 26
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.56,
|
104 |
+
"grad_norm": 2.16381573677063,
|
105 |
+
"learning_rate": 4.518518518518519e-05,
|
106 |
+
"loss": 0.6739,
|
107 |
+
"step": 28
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.6,
|
111 |
+
"grad_norm": 2.6895177364349365,
|
112 |
+
"learning_rate": 4.4444444444444447e-05,
|
113 |
+
"loss": 0.6952,
|
114 |
+
"step": 30
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.64,
|
118 |
+
"grad_norm": 3.0539653301239014,
|
119 |
+
"learning_rate": 4.3703703703703705e-05,
|
120 |
+
"loss": 0.6916,
|
121 |
+
"step": 32
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.68,
|
125 |
+
"grad_norm": 1.6905677318572998,
|
126 |
+
"learning_rate": 4.296296296296296e-05,
|
127 |
+
"loss": 0.7039,
|
128 |
+
"step": 34
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.72,
|
132 |
+
"grad_norm": 1.9867430925369263,
|
133 |
+
"learning_rate": 4.222222222222222e-05,
|
134 |
+
"loss": 0.5762,
|
135 |
+
"step": 36
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.76,
|
139 |
+
"grad_norm": 2.075601816177368,
|
140 |
+
"learning_rate": 4.148148148148148e-05,
|
141 |
+
"loss": 0.6578,
|
142 |
+
"step": 38
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.8,
|
146 |
+
"grad_norm": 2.779691219329834,
|
147 |
+
"learning_rate": 4.074074074074074e-05,
|
148 |
+
"loss": 0.6646,
|
149 |
+
"step": 40
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.84,
|
153 |
+
"grad_norm": 2.750957489013672,
|
154 |
+
"learning_rate": 4e-05,
|
155 |
+
"loss": 0.5964,
|
156 |
+
"step": 42
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.88,
|
160 |
+
"grad_norm": 2.7763702869415283,
|
161 |
+
"learning_rate": 3.925925925925926e-05,
|
162 |
+
"loss": 0.6092,
|
163 |
+
"step": 44
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.92,
|
167 |
+
"grad_norm": 3.3457367420196533,
|
168 |
+
"learning_rate": 3.851851851851852e-05,
|
169 |
+
"loss": 0.5502,
|
170 |
+
"step": 46
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.96,
|
174 |
+
"grad_norm": 2.7507972717285156,
|
175 |
+
"learning_rate": 3.777777777777778e-05,
|
176 |
+
"loss": 0.5042,
|
177 |
+
"step": 48
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.0,
|
181 |
+
"grad_norm": 4.478252410888672,
|
182 |
+
"learning_rate": 3.7037037037037037e-05,
|
183 |
+
"loss": 0.6469,
|
184 |
+
"step": 50
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.0,
|
188 |
+
"eval_accuracy": 0.7,
|
189 |
+
"eval_auc": 0.8071999999999999,
|
190 |
+
"eval_f1": 0.7169811320754716,
|
191 |
+
"eval_loss": 0.5654460787773132,
|
192 |
+
"eval_precision": 0.6785714285714286,
|
193 |
+
"eval_recall": 0.76,
|
194 |
+
"eval_runtime": 7.9595,
|
195 |
+
"eval_samples_per_second": 12.564,
|
196 |
+
"eval_steps_per_second": 0.879,
|
197 |
+
"step": 50
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.04,
|
201 |
+
"grad_norm": 2.6288881301879883,
|
202 |
+
"learning_rate": 3.62962962962963e-05,
|
203 |
+
"loss": 0.3589,
|
204 |
+
"step": 52
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 1.08,
|
208 |
+
"grad_norm": 4.38114595413208,
|
209 |
+
"learning_rate": 3.555555555555556e-05,
|
210 |
+
"loss": 0.408,
|
211 |
+
"step": 54
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 1.12,
|
215 |
+
"grad_norm": 6.498011589050293,
|
216 |
+
"learning_rate": 3.481481481481482e-05,
|
217 |
+
"loss": 0.3517,
|
218 |
+
"step": 56
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.16,
|
222 |
+
"grad_norm": 7.760722637176514,
|
223 |
+
"learning_rate": 3.4074074074074077e-05,
|
224 |
+
"loss": 0.3926,
|
225 |
+
"step": 58
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 1.2,
|
229 |
+
"grad_norm": 8.327621459960938,
|
230 |
+
"learning_rate": 3.3333333333333335e-05,
|
231 |
+
"loss": 0.2361,
|
232 |
+
"step": 60
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 1.24,
|
236 |
+
"grad_norm": 3.809370756149292,
|
237 |
+
"learning_rate": 3.25925925925926e-05,
|
238 |
+
"loss": 0.3742,
|
239 |
+
"step": 62
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.28,
|
243 |
+
"grad_norm": 12.8309965133667,
|
244 |
+
"learning_rate": 3.185185185185185e-05,
|
245 |
+
"loss": 0.576,
|
246 |
+
"step": 64
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 1.32,
|
250 |
+
"grad_norm": 9.91649055480957,
|
251 |
+
"learning_rate": 3.111111111111111e-05,
|
252 |
+
"loss": 0.808,
|
253 |
+
"step": 66
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 1.3599999999999999,
|
257 |
+
"grad_norm": 9.183283805847168,
|
258 |
+
"learning_rate": 3.037037037037037e-05,
|
259 |
+
"loss": 0.5811,
|
260 |
+
"step": 68
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.4,
|
264 |
+
"grad_norm": 10.989977836608887,
|
265 |
+
"learning_rate": 2.962962962962963e-05,
|
266 |
+
"loss": 0.2667,
|
267 |
+
"step": 70
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 1.44,
|
271 |
+
"grad_norm": 12.52010726928711,
|
272 |
+
"learning_rate": 2.8888888888888888e-05,
|
273 |
+
"loss": 0.7402,
|
274 |
+
"step": 72
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 1.48,
|
278 |
+
"grad_norm": 5.40288782119751,
|
279 |
+
"learning_rate": 2.814814814814815e-05,
|
280 |
+
"loss": 0.3061,
|
281 |
+
"step": 74
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.52,
|
285 |
+
"grad_norm": 7.423550128936768,
|
286 |
+
"learning_rate": 2.7407407407407408e-05,
|
287 |
+
"loss": 0.4198,
|
288 |
+
"step": 76
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 1.56,
|
292 |
+
"grad_norm": 9.907425880432129,
|
293 |
+
"learning_rate": 2.6666666666666667e-05,
|
294 |
+
"loss": 0.4816,
|
295 |
+
"step": 78
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 1.6,
|
299 |
+
"grad_norm": 7.145705699920654,
|
300 |
+
"learning_rate": 2.5925925925925925e-05,
|
301 |
+
"loss": 0.3788,
|
302 |
+
"step": 80
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.6400000000000001,
|
306 |
+
"grad_norm": 1.4431923627853394,
|
307 |
+
"learning_rate": 2.5185185185185183e-05,
|
308 |
+
"loss": 0.3837,
|
309 |
+
"step": 82
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 1.6800000000000002,
|
313 |
+
"grad_norm": 8.11041259765625,
|
314 |
+
"learning_rate": 2.4444444444444445e-05,
|
315 |
+
"loss": 0.5001,
|
316 |
+
"step": 84
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 1.72,
|
320 |
+
"grad_norm": 8.253824234008789,
|
321 |
+
"learning_rate": 2.3703703703703707e-05,
|
322 |
+
"loss": 0.6369,
|
323 |
+
"step": 86
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 1.76,
|
327 |
+
"grad_norm": 4.3440937995910645,
|
328 |
+
"learning_rate": 2.2962962962962965e-05,
|
329 |
+
"loss": 0.3467,
|
330 |
+
"step": 88
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 1.8,
|
334 |
+
"grad_norm": 2.9534313678741455,
|
335 |
+
"learning_rate": 2.2222222222222223e-05,
|
336 |
+
"loss": 0.2029,
|
337 |
+
"step": 90
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 1.8399999999999999,
|
341 |
+
"grad_norm": 3.6825966835021973,
|
342 |
+
"learning_rate": 2.148148148148148e-05,
|
343 |
+
"loss": 0.3657,
|
344 |
+
"step": 92
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.88,
|
348 |
+
"grad_norm": 8.141383171081543,
|
349 |
+
"learning_rate": 2.074074074074074e-05,
|
350 |
+
"loss": 0.5135,
|
351 |
+
"step": 94
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 1.92,
|
355 |
+
"grad_norm": 23.226926803588867,
|
356 |
+
"learning_rate": 2e-05,
|
357 |
+
"loss": 0.8375,
|
358 |
+
"step": 96
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 1.96,
|
362 |
+
"grad_norm": 7.735658645629883,
|
363 |
+
"learning_rate": 1.925925925925926e-05,
|
364 |
+
"loss": 0.3536,
|
365 |
+
"step": 98
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 2.0,
|
369 |
+
"grad_norm": 11.800036430358887,
|
370 |
+
"learning_rate": 1.8518518518518518e-05,
|
371 |
+
"loss": 0.294,
|
372 |
+
"step": 100
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 2.0,
|
376 |
+
"eval_accuracy": 0.77,
|
377 |
+
"eval_auc": 0.8512,
|
378 |
+
"eval_f1": 0.7722772277227723,
|
379 |
+
"eval_loss": 0.5280066132545471,
|
380 |
+
"eval_precision": 0.7647058823529411,
|
381 |
+
"eval_recall": 0.78,
|
382 |
+
"eval_runtime": 7.9925,
|
383 |
+
"eval_samples_per_second": 12.512,
|
384 |
+
"eval_steps_per_second": 0.876,
|
385 |
+
"step": 100
|
386 |
+
}
|
387 |
+
],
|
388 |
+
"logging_steps": 2,
|
389 |
+
"max_steps": 150,
|
390 |
+
"num_input_tokens_seen": 0,
|
391 |
+
"num_train_epochs": 3,
|
392 |
+
"save_steps": 500,
|
393 |
+
"total_flos": 26493479731200.0,
|
394 |
+
"train_batch_size": 8,
|
395 |
+
"trial_name": null,
|
396 |
+
"trial_params": null
|
397 |
+
}
|
checkpoint-100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5829f9bce5817d1168ff56d8713711db6df414d638e2bdc87ce68301e45a1ae0
|
3 |
+
size 5048
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
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": "4.40.1",
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56506cb937e6f93862e5353ebf31545e12778460f4b84b6ec8d7a8f02a0ad16c
|
3 |
+
size 267832560
|
runs/May16_00-59-57_r-bjankav-neurips-bert-x7eyfjr1-9733e-32r9k/events.out.tfevents.1715821197.r-bjankav-neurips-bert-x7eyfjr1-9733e-32r9k.87.0
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:b34f9a7f24f778a7476245b493bdd9daf98fca97892fb7878cd813915dc9b1ed
|
3 |
+
size 22184
|
runs/May16_00-59-57_r-bjankav-neurips-bert-x7eyfjr1-9733e-32r9k/events.out.tfevents.1715821608.r-bjankav-neurips-bert-x7eyfjr1-9733e-32r9k.87.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf7e7469f6bdca580637a3a439e58bb541592f0a5e7de9a2fa4297a378f3c347
|
3 |
+
size 607
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5829f9bce5817d1168ff56d8713711db6df414d638e2bdc87ce68301e45a1ae0
|
3 |
+
size 5048
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "neurips-bert-combined2/autotrain-data",
|
3 |
+
"model": "distilbert/distilbert-base-uncased",
|
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": "neurips-bert-combined2",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": null,
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"evaluation_strategy": "epoch",
|
26 |
+
"username": "BjankaV",
|
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
|
|