Bjanka Vrljić
commited on
Commit
•
e4e67d5
1
Parent(s):
5513ef1
Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-72/config.json +34 -0
- checkpoint-72/model.safetensors +3 -0
- checkpoint-72/optimizer.pt +3 -0
- checkpoint-72/rng_state.pth +3 -0
- checkpoint-72/scheduler.pt +3 -0
- checkpoint-72/trainer_state.json +564 -0
- checkpoint-72/training_args.bin +3 -0
- config.json +34 -0
- model.safetensors +3 -0
- runs/May16_04-09-10_r-bjankav-neurips-bert-lxjn8hi1-2e204-b5evc/events.out.tfevents.1715832550.r-bjankav-neurips-bert-lxjn8hi1-2e204-b5evc.84.0 +2 -2
- runs/May16_04-09-10_r-bjankav-neurips-bert-lxjn8hi1-2e204-b5evc/events.out.tfevents.1715832770.r-bjankav-neurips-bert-lxjn8hi1-2e204-b5evc.84.1 +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-covid2/autotrain-data
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 0.4708668887615204
|
18 |
+
|
19 |
+
f1: 0.7111111111111111
|
20 |
+
|
21 |
+
precision: 0.7619047619047619
|
22 |
+
|
23 |
+
recall: 0.6666666666666666
|
24 |
+
|
25 |
+
auc: 0.8819444444444444
|
26 |
+
|
27 |
+
accuracy: 0.7291666666666666
|
checkpoint-72/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-72/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da58269952ed95da4221ede4094af02a4f69ac5fcad0dbf620ce3fe4276e146a
|
3 |
+
size 267832560
|
checkpoint-72/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1e071c1d8a40c020b789c21506cd9fc2d9599de3ca7added69a40b609d1df95
|
3 |
+
size 535724410
|
checkpoint-72/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a1d06a10767b71cad73d354c1f4f8253919ef6d51507019db9a0188ef7f1393
|
3 |
+
size 13990
|
checkpoint-72/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a579940d4b286b344017c01f122e511e16ebf080c79a25a71772097a15afca9
|
3 |
+
size 1064
|
checkpoint-72/trainer_state.json
ADDED
@@ -0,0 +1,564 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4708668887615204,
|
3 |
+
"best_model_checkpoint": "neurips-bert-covid2/checkpoint-72",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 72,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.041666666666666664,
|
13 |
+
"grad_norm": 1.8110902309417725,
|
14 |
+
"learning_rate": 6.25e-06,
|
15 |
+
"loss": 0.7085,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.08333333333333333,
|
20 |
+
"grad_norm": 1.516195297241211,
|
21 |
+
"learning_rate": 1.25e-05,
|
22 |
+
"loss": 0.6936,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.125,
|
27 |
+
"grad_norm": 1.5400855541229248,
|
28 |
+
"learning_rate": 1.8750000000000002e-05,
|
29 |
+
"loss": 0.6962,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.16666666666666666,
|
34 |
+
"grad_norm": 1.5547490119934082,
|
35 |
+
"learning_rate": 2.5e-05,
|
36 |
+
"loss": 0.6856,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.20833333333333334,
|
41 |
+
"grad_norm": 1.9711639881134033,
|
42 |
+
"learning_rate": 3.125e-05,
|
43 |
+
"loss": 0.7146,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.25,
|
48 |
+
"grad_norm": 1.240113377571106,
|
49 |
+
"learning_rate": 3.7500000000000003e-05,
|
50 |
+
"loss": 0.6961,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.2916666666666667,
|
55 |
+
"grad_norm": 2.8544723987579346,
|
56 |
+
"learning_rate": 4.375e-05,
|
57 |
+
"loss": 0.7225,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.3333333333333333,
|
62 |
+
"grad_norm": 1.5479539632797241,
|
63 |
+
"learning_rate": 5e-05,
|
64 |
+
"loss": 0.6805,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.375,
|
69 |
+
"grad_norm": 2.501298189163208,
|
70 |
+
"learning_rate": 4.921875e-05,
|
71 |
+
"loss": 0.6827,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.4166666666666667,
|
76 |
+
"grad_norm": 1.2585351467132568,
|
77 |
+
"learning_rate": 4.8437500000000005e-05,
|
78 |
+
"loss": 0.6913,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.4583333333333333,
|
83 |
+
"grad_norm": 2.8580899238586426,
|
84 |
+
"learning_rate": 4.765625e-05,
|
85 |
+
"loss": 0.7193,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.5,
|
90 |
+
"grad_norm": 1.8804811239242554,
|
91 |
+
"learning_rate": 4.6875e-05,
|
92 |
+
"loss": 0.6775,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.5416666666666666,
|
97 |
+
"grad_norm": 1.819166660308838,
|
98 |
+
"learning_rate": 4.609375e-05,
|
99 |
+
"loss": 0.6837,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.5833333333333334,
|
104 |
+
"grad_norm": 5.167153835296631,
|
105 |
+
"learning_rate": 4.5312500000000004e-05,
|
106 |
+
"loss": 0.7496,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.625,
|
111 |
+
"grad_norm": 2.7906579971313477,
|
112 |
+
"learning_rate": 4.453125e-05,
|
113 |
+
"loss": 0.668,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.6666666666666666,
|
118 |
+
"grad_norm": 2.066265821456909,
|
119 |
+
"learning_rate": 4.375e-05,
|
120 |
+
"loss": 0.7059,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.7083333333333334,
|
125 |
+
"grad_norm": 1.6561486721038818,
|
126 |
+
"learning_rate": 4.2968750000000004e-05,
|
127 |
+
"loss": 0.6754,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.75,
|
132 |
+
"grad_norm": 1.295357584953308,
|
133 |
+
"learning_rate": 4.21875e-05,
|
134 |
+
"loss": 0.7039,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.7916666666666666,
|
139 |
+
"grad_norm": 1.3129117488861084,
|
140 |
+
"learning_rate": 4.140625e-05,
|
141 |
+
"loss": 0.6769,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.8333333333333334,
|
146 |
+
"grad_norm": 1.9816412925720215,
|
147 |
+
"learning_rate": 4.0625000000000005e-05,
|
148 |
+
"loss": 0.7029,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.875,
|
153 |
+
"grad_norm": 1.9955068826675415,
|
154 |
+
"learning_rate": 3.984375e-05,
|
155 |
+
"loss": 0.7002,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.9166666666666666,
|
160 |
+
"grad_norm": 1.2235780954360962,
|
161 |
+
"learning_rate": 3.90625e-05,
|
162 |
+
"loss": 0.6692,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.9583333333333334,
|
167 |
+
"grad_norm": 1.2365633249282837,
|
168 |
+
"learning_rate": 3.828125e-05,
|
169 |
+
"loss": 0.6925,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.0,
|
174 |
+
"grad_norm": 4.916609764099121,
|
175 |
+
"learning_rate": 3.7500000000000003e-05,
|
176 |
+
"loss": 0.5837,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.0,
|
181 |
+
"eval_accuracy": 0.5625,
|
182 |
+
"eval_auc": 0.8472222222222222,
|
183 |
+
"eval_f1": 0.6956521739130435,
|
184 |
+
"eval_loss": 0.6709879040718079,
|
185 |
+
"eval_precision": 0.5333333333333333,
|
186 |
+
"eval_recall": 1.0,
|
187 |
+
"eval_runtime": 4.4819,
|
188 |
+
"eval_samples_per_second": 10.71,
|
189 |
+
"eval_steps_per_second": 0.669,
|
190 |
+
"step": 24
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 1.0416666666666667,
|
194 |
+
"grad_norm": 1.8808804750442505,
|
195 |
+
"learning_rate": 3.671875e-05,
|
196 |
+
"loss": 0.648,
|
197 |
+
"step": 25
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.0833333333333333,
|
201 |
+
"grad_norm": 1.5214107036590576,
|
202 |
+
"learning_rate": 3.59375e-05,
|
203 |
+
"loss": 0.6867,
|
204 |
+
"step": 26
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 1.125,
|
208 |
+
"grad_norm": 3.7438745498657227,
|
209 |
+
"learning_rate": 3.5156250000000004e-05,
|
210 |
+
"loss": 0.7164,
|
211 |
+
"step": 27
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 1.1666666666666667,
|
215 |
+
"grad_norm": 1.6739788055419922,
|
216 |
+
"learning_rate": 3.4375e-05,
|
217 |
+
"loss": 0.6204,
|
218 |
+
"step": 28
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.2083333333333333,
|
222 |
+
"grad_norm": 2.76830792427063,
|
223 |
+
"learning_rate": 3.359375e-05,
|
224 |
+
"loss": 0.6222,
|
225 |
+
"step": 29
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 1.25,
|
229 |
+
"grad_norm": 3.7020490169525146,
|
230 |
+
"learning_rate": 3.2812500000000005e-05,
|
231 |
+
"loss": 0.4947,
|
232 |
+
"step": 30
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 1.2916666666666667,
|
236 |
+
"grad_norm": 3.1208748817443848,
|
237 |
+
"learning_rate": 3.203125e-05,
|
238 |
+
"loss": 0.5351,
|
239 |
+
"step": 31
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.3333333333333333,
|
243 |
+
"grad_norm": 5.230617046356201,
|
244 |
+
"learning_rate": 3.125e-05,
|
245 |
+
"loss": 0.7481,
|
246 |
+
"step": 32
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 1.375,
|
250 |
+
"grad_norm": 5.657607555389404,
|
251 |
+
"learning_rate": 3.0468750000000002e-05,
|
252 |
+
"loss": 0.7248,
|
253 |
+
"step": 33
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 1.4166666666666667,
|
257 |
+
"grad_norm": 3.6821396350860596,
|
258 |
+
"learning_rate": 2.96875e-05,
|
259 |
+
"loss": 0.6446,
|
260 |
+
"step": 34
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.4583333333333333,
|
264 |
+
"grad_norm": 5.469022274017334,
|
265 |
+
"learning_rate": 2.890625e-05,
|
266 |
+
"loss": 0.6906,
|
267 |
+
"step": 35
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 1.5,
|
271 |
+
"grad_norm": 3.4459424018859863,
|
272 |
+
"learning_rate": 2.8125000000000003e-05,
|
273 |
+
"loss": 0.6416,
|
274 |
+
"step": 36
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 1.5416666666666665,
|
278 |
+
"grad_norm": 5.04787015914917,
|
279 |
+
"learning_rate": 2.734375e-05,
|
280 |
+
"loss": 0.5623,
|
281 |
+
"step": 37
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.5833333333333335,
|
285 |
+
"grad_norm": 4.515984058380127,
|
286 |
+
"learning_rate": 2.6562500000000002e-05,
|
287 |
+
"loss": 0.7856,
|
288 |
+
"step": 38
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 1.625,
|
292 |
+
"grad_norm": 5.653531551361084,
|
293 |
+
"learning_rate": 2.578125e-05,
|
294 |
+
"loss": 0.685,
|
295 |
+
"step": 39
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 1.6666666666666665,
|
299 |
+
"grad_norm": 3.044747829437256,
|
300 |
+
"learning_rate": 2.5e-05,
|
301 |
+
"loss": 0.6061,
|
302 |
+
"step": 40
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.7083333333333335,
|
306 |
+
"grad_norm": 3.404170036315918,
|
307 |
+
"learning_rate": 2.4218750000000003e-05,
|
308 |
+
"loss": 0.6479,
|
309 |
+
"step": 41
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 1.75,
|
313 |
+
"grad_norm": 4.791858673095703,
|
314 |
+
"learning_rate": 2.34375e-05,
|
315 |
+
"loss": 0.5555,
|
316 |
+
"step": 42
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 1.7916666666666665,
|
320 |
+
"grad_norm": 2.592275381088257,
|
321 |
+
"learning_rate": 2.2656250000000002e-05,
|
322 |
+
"loss": 0.4623,
|
323 |
+
"step": 43
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 1.8333333333333335,
|
327 |
+
"grad_norm": 3.900108575820923,
|
328 |
+
"learning_rate": 2.1875e-05,
|
329 |
+
"loss": 0.7635,
|
330 |
+
"step": 44
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 1.875,
|
334 |
+
"grad_norm": 2.6947779655456543,
|
335 |
+
"learning_rate": 2.109375e-05,
|
336 |
+
"loss": 0.5053,
|
337 |
+
"step": 45
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 1.9166666666666665,
|
341 |
+
"grad_norm": 3.176859140396118,
|
342 |
+
"learning_rate": 2.0312500000000002e-05,
|
343 |
+
"loss": 0.4846,
|
344 |
+
"step": 46
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.9583333333333335,
|
348 |
+
"grad_norm": 4.098372936248779,
|
349 |
+
"learning_rate": 1.953125e-05,
|
350 |
+
"loss": 0.4985,
|
351 |
+
"step": 47
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 2.0,
|
355 |
+
"grad_norm": 8.404435157775879,
|
356 |
+
"learning_rate": 1.8750000000000002e-05,
|
357 |
+
"loss": 0.8451,
|
358 |
+
"step": 48
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 2.0,
|
362 |
+
"eval_accuracy": 0.7708333333333334,
|
363 |
+
"eval_auc": 0.876736111111111,
|
364 |
+
"eval_f1": 0.7317073170731707,
|
365 |
+
"eval_loss": 0.5312010645866394,
|
366 |
+
"eval_precision": 0.8823529411764706,
|
367 |
+
"eval_recall": 0.625,
|
368 |
+
"eval_runtime": 4.4463,
|
369 |
+
"eval_samples_per_second": 10.795,
|
370 |
+
"eval_steps_per_second": 0.675,
|
371 |
+
"step": 48
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 2.0416666666666665,
|
375 |
+
"grad_norm": 3.8697705268859863,
|
376 |
+
"learning_rate": 1.796875e-05,
|
377 |
+
"loss": 0.4105,
|
378 |
+
"step": 49
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 2.0833333333333335,
|
382 |
+
"grad_norm": 3.5727429389953613,
|
383 |
+
"learning_rate": 1.71875e-05,
|
384 |
+
"loss": 0.5534,
|
385 |
+
"step": 50
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 2.125,
|
389 |
+
"grad_norm": 5.1031694412231445,
|
390 |
+
"learning_rate": 1.6406250000000002e-05,
|
391 |
+
"loss": 0.6683,
|
392 |
+
"step": 51
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 2.1666666666666665,
|
396 |
+
"grad_norm": 2.927239418029785,
|
397 |
+
"learning_rate": 1.5625e-05,
|
398 |
+
"loss": 0.3466,
|
399 |
+
"step": 52
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 2.2083333333333335,
|
403 |
+
"grad_norm": 4.0092291831970215,
|
404 |
+
"learning_rate": 1.484375e-05,
|
405 |
+
"loss": 0.4766,
|
406 |
+
"step": 53
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 2.25,
|
410 |
+
"grad_norm": 3.152967691421509,
|
411 |
+
"learning_rate": 1.4062500000000001e-05,
|
412 |
+
"loss": 0.3449,
|
413 |
+
"step": 54
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 2.2916666666666665,
|
417 |
+
"grad_norm": 4.670276641845703,
|
418 |
+
"learning_rate": 1.3281250000000001e-05,
|
419 |
+
"loss": 0.357,
|
420 |
+
"step": 55
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 2.3333333333333335,
|
424 |
+
"grad_norm": 3.458336353302002,
|
425 |
+
"learning_rate": 1.25e-05,
|
426 |
+
"loss": 0.3465,
|
427 |
+
"step": 56
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 2.375,
|
431 |
+
"grad_norm": 4.430357456207275,
|
432 |
+
"learning_rate": 1.171875e-05,
|
433 |
+
"loss": 0.4588,
|
434 |
+
"step": 57
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 2.4166666666666665,
|
438 |
+
"grad_norm": 3.3026180267333984,
|
439 |
+
"learning_rate": 1.09375e-05,
|
440 |
+
"loss": 0.5152,
|
441 |
+
"step": 58
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 2.4583333333333335,
|
445 |
+
"grad_norm": 5.186245441436768,
|
446 |
+
"learning_rate": 1.0156250000000001e-05,
|
447 |
+
"loss": 0.509,
|
448 |
+
"step": 59
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 2.5,
|
452 |
+
"grad_norm": 2.922844648361206,
|
453 |
+
"learning_rate": 9.375000000000001e-06,
|
454 |
+
"loss": 0.2758,
|
455 |
+
"step": 60
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 2.5416666666666665,
|
459 |
+
"grad_norm": 3.419301986694336,
|
460 |
+
"learning_rate": 8.59375e-06,
|
461 |
+
"loss": 0.2875,
|
462 |
+
"step": 61
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 2.5833333333333335,
|
466 |
+
"grad_norm": 7.4599609375,
|
467 |
+
"learning_rate": 7.8125e-06,
|
468 |
+
"loss": 0.4698,
|
469 |
+
"step": 62
|
470 |
+
},
|
471 |
+
{
|
472 |
+
"epoch": 2.625,
|
473 |
+
"grad_norm": 5.62416410446167,
|
474 |
+
"learning_rate": 7.031250000000001e-06,
|
475 |
+
"loss": 0.2694,
|
476 |
+
"step": 63
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 2.6666666666666665,
|
480 |
+
"grad_norm": 2.9614017009735107,
|
481 |
+
"learning_rate": 6.25e-06,
|
482 |
+
"loss": 0.332,
|
483 |
+
"step": 64
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 2.7083333333333335,
|
487 |
+
"grad_norm": 3.8540635108947754,
|
488 |
+
"learning_rate": 5.46875e-06,
|
489 |
+
"loss": 0.3257,
|
490 |
+
"step": 65
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 2.75,
|
494 |
+
"grad_norm": 5.815990924835205,
|
495 |
+
"learning_rate": 4.6875000000000004e-06,
|
496 |
+
"loss": 0.4957,
|
497 |
+
"step": 66
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 2.7916666666666665,
|
501 |
+
"grad_norm": 4.854381084442139,
|
502 |
+
"learning_rate": 3.90625e-06,
|
503 |
+
"loss": 0.5122,
|
504 |
+
"step": 67
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 2.8333333333333335,
|
508 |
+
"grad_norm": 4.338609218597412,
|
509 |
+
"learning_rate": 3.125e-06,
|
510 |
+
"loss": 0.2326,
|
511 |
+
"step": 68
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 2.875,
|
515 |
+
"grad_norm": 7.25624942779541,
|
516 |
+
"learning_rate": 2.3437500000000002e-06,
|
517 |
+
"loss": 0.4954,
|
518 |
+
"step": 69
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 2.9166666666666665,
|
522 |
+
"grad_norm": 4.799122333526611,
|
523 |
+
"learning_rate": 1.5625e-06,
|
524 |
+
"loss": 0.3148,
|
525 |
+
"step": 70
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 2.9583333333333335,
|
529 |
+
"grad_norm": 4.962360382080078,
|
530 |
+
"learning_rate": 7.8125e-07,
|
531 |
+
"loss": 0.4699,
|
532 |
+
"step": 71
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 3.0,
|
536 |
+
"grad_norm": 6.431361198425293,
|
537 |
+
"learning_rate": 0.0,
|
538 |
+
"loss": 0.4453,
|
539 |
+
"step": 72
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 3.0,
|
543 |
+
"eval_accuracy": 0.7291666666666666,
|
544 |
+
"eval_auc": 0.8819444444444444,
|
545 |
+
"eval_f1": 0.7111111111111111,
|
546 |
+
"eval_loss": 0.4708668887615204,
|
547 |
+
"eval_precision": 0.7619047619047619,
|
548 |
+
"eval_recall": 0.6666666666666666,
|
549 |
+
"eval_runtime": 3.8968,
|
550 |
+
"eval_samples_per_second": 12.318,
|
551 |
+
"eval_steps_per_second": 0.77,
|
552 |
+
"step": 72
|
553 |
+
}
|
554 |
+
],
|
555 |
+
"logging_steps": 1,
|
556 |
+
"max_steps": 72,
|
557 |
+
"num_input_tokens_seen": 0,
|
558 |
+
"num_train_epochs": 3,
|
559 |
+
"save_steps": 500,
|
560 |
+
"total_flos": 18677903210496.0,
|
561 |
+
"train_batch_size": 8,
|
562 |
+
"trial_name": null,
|
563 |
+
"trial_params": null
|
564 |
+
}
|
checkpoint-72/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7be0563f71b4df33a6b3b92bdbbb334ed44434bb485337a65fe34764e4a86e72
|
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:da58269952ed95da4221ede4094af02a4f69ac5fcad0dbf620ce3fe4276e146a
|
3 |
+
size 267832560
|
runs/May16_04-09-10_r-bjankav-neurips-bert-lxjn8hi1-2e204-b5evc/events.out.tfevents.1715832550.r-bjankav-neurips-bert-lxjn8hi1-2e204-b5evc.84.0
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 sha256:149da627994df78332e4d8c0dbf643f72fa73ebd44737d1e2bc3a67a0aac2a40
|
3 |
+
size 21490
|
runs/May16_04-09-10_r-bjankav-neurips-bert-lxjn8hi1-2e204-b5evc/events.out.tfevents.1715832770.r-bjankav-neurips-bert-lxjn8hi1-2e204-b5evc.84.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:272e096c3b846b4ee43342a17a64c9cbc8c01f104e4efeb061d787b934d2f12b
|
3 |
+
size 597
|
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 sha256:7be0563f71b4df33a6b3b92bdbbb334ed44434bb485337a65fe34764e4a86e72
|
3 |
+
size 5048
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "neurips-bert-covid2/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-covid2",
|
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
|
|