Bjanka Vrljić
commited on
Commit
•
c4ac465
1
Parent(s):
7fe70f9
Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-100/config.json +36 -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 +36 -0
- model.safetensors +3 -0
- runs/May16_00-39-43_r-bjankav-neurips-bert-ixe8k41t-07e80-8p5jg/events.out.tfevents.1715819983.r-bjankav-neurips-bert-ixe8k41t-07e80-8p5jg.87.0 +2 -2
- runs/May16_00-39-43_r-bjankav-neurips-bert-ixe8k41t-07e80-8p5jg/events.out.tfevents.1715820781.r-bjankav-neurips-bert-ixe8k41t-07e80-8p5jg.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-combined1/autotrain-data
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 0.5809483528137207
|
18 |
+
|
19 |
+
f1: 0.6265060240963856
|
20 |
+
|
21 |
+
precision: 0.7878787878787878
|
22 |
+
|
23 |
+
recall: 0.52
|
24 |
+
|
25 |
+
auc: 0.8136
|
26 |
+
|
27 |
+
accuracy: 0.69
|
checkpoint-100/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "0",
|
15 |
+
"1": "1"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"0": 0,
|
21 |
+
"1": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "bert",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.40.1",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 30522
|
36 |
+
}
|
checkpoint-100/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fd255e3b9cc12c5fe17d59cff701cb1c35b26f77581d23182af7f7a66af07a5
|
3 |
+
size 437958648
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63163e5cabfabf9add6647651f09e3432b64b03b33a9a6c8a26ca2314168e52d
|
3 |
+
size 876032762
|
checkpoint-100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1a4a06037767fca0f8e213e0983296d1489d0cf42a855765005494719dfc1cc
|
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": 0.5809483528137207,
|
3 |
+
"best_model_checkpoint": "neurips-bert-combined1/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": 3.577862501144409,
|
14 |
+
"learning_rate": 6.666666666666667e-06,
|
15 |
+
"loss": 0.6737,
|
16 |
+
"step": 2
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.08,
|
20 |
+
"grad_norm": 5.035987377166748,
|
21 |
+
"learning_rate": 1.3333333333333333e-05,
|
22 |
+
"loss": 0.6841,
|
23 |
+
"step": 4
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.12,
|
27 |
+
"grad_norm": 3.1154258251190186,
|
28 |
+
"learning_rate": 2e-05,
|
29 |
+
"loss": 0.7756,
|
30 |
+
"step": 6
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.16,
|
34 |
+
"grad_norm": 10.06010627746582,
|
35 |
+
"learning_rate": 2.6666666666666667e-05,
|
36 |
+
"loss": 0.7759,
|
37 |
+
"step": 8
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.2,
|
41 |
+
"grad_norm": 7.218173503875732,
|
42 |
+
"learning_rate": 3.3333333333333335e-05,
|
43 |
+
"loss": 0.7774,
|
44 |
+
"step": 10
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.24,
|
48 |
+
"grad_norm": 9.524176597595215,
|
49 |
+
"learning_rate": 4e-05,
|
50 |
+
"loss": 0.74,
|
51 |
+
"step": 12
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.28,
|
55 |
+
"grad_norm": 3.1684250831604004,
|
56 |
+
"learning_rate": 4.666666666666667e-05,
|
57 |
+
"loss": 0.6328,
|
58 |
+
"step": 14
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.32,
|
62 |
+
"grad_norm": 9.243531227111816,
|
63 |
+
"learning_rate": 4.962962962962963e-05,
|
64 |
+
"loss": 0.6749,
|
65 |
+
"step": 16
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.36,
|
69 |
+
"grad_norm": 15.164690971374512,
|
70 |
+
"learning_rate": 4.888888888888889e-05,
|
71 |
+
"loss": 0.7968,
|
72 |
+
"step": 18
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.4,
|
76 |
+
"grad_norm": 4.498668193817139,
|
77 |
+
"learning_rate": 4.814814814814815e-05,
|
78 |
+
"loss": 0.7803,
|
79 |
+
"step": 20
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.44,
|
83 |
+
"grad_norm": 10.785091400146484,
|
84 |
+
"learning_rate": 4.740740740740741e-05,
|
85 |
+
"loss": 0.6634,
|
86 |
+
"step": 22
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.48,
|
90 |
+
"grad_norm": 4.868218421936035,
|
91 |
+
"learning_rate": 4.666666666666667e-05,
|
92 |
+
"loss": 0.6974,
|
93 |
+
"step": 24
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.52,
|
97 |
+
"grad_norm": 6.348710060119629,
|
98 |
+
"learning_rate": 4.592592592592593e-05,
|
99 |
+
"loss": 0.6492,
|
100 |
+
"step": 26
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.56,
|
104 |
+
"grad_norm": 6.30601692199707,
|
105 |
+
"learning_rate": 4.518518518518519e-05,
|
106 |
+
"loss": 0.7361,
|
107 |
+
"step": 28
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.6,
|
111 |
+
"grad_norm": 6.230818748474121,
|
112 |
+
"learning_rate": 4.4444444444444447e-05,
|
113 |
+
"loss": 0.6889,
|
114 |
+
"step": 30
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.64,
|
118 |
+
"grad_norm": 7.42860221862793,
|
119 |
+
"learning_rate": 4.3703703703703705e-05,
|
120 |
+
"loss": 0.6431,
|
121 |
+
"step": 32
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.68,
|
125 |
+
"grad_norm": 2.7333102226257324,
|
126 |
+
"learning_rate": 4.296296296296296e-05,
|
127 |
+
"loss": 0.7148,
|
128 |
+
"step": 34
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.72,
|
132 |
+
"grad_norm": 3.3061561584472656,
|
133 |
+
"learning_rate": 4.222222222222222e-05,
|
134 |
+
"loss": 0.6978,
|
135 |
+
"step": 36
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.76,
|
139 |
+
"grad_norm": 3.080080032348633,
|
140 |
+
"learning_rate": 4.148148148148148e-05,
|
141 |
+
"loss": 0.7332,
|
142 |
+
"step": 38
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.8,
|
146 |
+
"grad_norm": 2.468094825744629,
|
147 |
+
"learning_rate": 4.074074074074074e-05,
|
148 |
+
"loss": 0.6837,
|
149 |
+
"step": 40
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.84,
|
153 |
+
"grad_norm": 4.740555286407471,
|
154 |
+
"learning_rate": 4e-05,
|
155 |
+
"loss": 0.7024,
|
156 |
+
"step": 42
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.88,
|
160 |
+
"grad_norm": 4.630310535430908,
|
161 |
+
"learning_rate": 3.925925925925926e-05,
|
162 |
+
"loss": 0.6951,
|
163 |
+
"step": 44
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.92,
|
167 |
+
"grad_norm": 2.2872023582458496,
|
168 |
+
"learning_rate": 3.851851851851852e-05,
|
169 |
+
"loss": 0.6575,
|
170 |
+
"step": 46
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.96,
|
174 |
+
"grad_norm": 3.9264609813690186,
|
175 |
+
"learning_rate": 3.777777777777778e-05,
|
176 |
+
"loss": 0.6714,
|
177 |
+
"step": 48
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.0,
|
181 |
+
"grad_norm": 3.6678338050842285,
|
182 |
+
"learning_rate": 3.7037037037037037e-05,
|
183 |
+
"loss": 0.6892,
|
184 |
+
"step": 50
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.0,
|
188 |
+
"eval_accuracy": 0.51,
|
189 |
+
"eval_auc": 0.7687999999999999,
|
190 |
+
"eval_f1": 0.6711409395973155,
|
191 |
+
"eval_loss": 0.6739338636398315,
|
192 |
+
"eval_precision": 0.5050505050505051,
|
193 |
+
"eval_recall": 1.0,
|
194 |
+
"eval_runtime": 16.1008,
|
195 |
+
"eval_samples_per_second": 6.211,
|
196 |
+
"eval_steps_per_second": 0.435,
|
197 |
+
"step": 50
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.04,
|
201 |
+
"grad_norm": 4.582466125488281,
|
202 |
+
"learning_rate": 3.62962962962963e-05,
|
203 |
+
"loss": 0.6436,
|
204 |
+
"step": 52
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 1.08,
|
208 |
+
"grad_norm": 6.386196613311768,
|
209 |
+
"learning_rate": 3.555555555555556e-05,
|
210 |
+
"loss": 0.6901,
|
211 |
+
"step": 54
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 1.12,
|
215 |
+
"grad_norm": 3.274430751800537,
|
216 |
+
"learning_rate": 3.481481481481482e-05,
|
217 |
+
"loss": 0.6233,
|
218 |
+
"step": 56
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.16,
|
222 |
+
"grad_norm": 8.776232719421387,
|
223 |
+
"learning_rate": 3.4074074074074077e-05,
|
224 |
+
"loss": 0.6726,
|
225 |
+
"step": 58
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 1.2,
|
229 |
+
"grad_norm": 8.833818435668945,
|
230 |
+
"learning_rate": 3.3333333333333335e-05,
|
231 |
+
"loss": 0.6303,
|
232 |
+
"step": 60
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 1.24,
|
236 |
+
"grad_norm": 7.453307628631592,
|
237 |
+
"learning_rate": 3.25925925925926e-05,
|
238 |
+
"loss": 0.6011,
|
239 |
+
"step": 62
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.28,
|
243 |
+
"grad_norm": 2.839207887649536,
|
244 |
+
"learning_rate": 3.185185185185185e-05,
|
245 |
+
"loss": 0.6144,
|
246 |
+
"step": 64
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 1.32,
|
250 |
+
"grad_norm": 5.08197546005249,
|
251 |
+
"learning_rate": 3.111111111111111e-05,
|
252 |
+
"loss": 0.716,
|
253 |
+
"step": 66
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 1.3599999999999999,
|
257 |
+
"grad_norm": 7.713846206665039,
|
258 |
+
"learning_rate": 3.037037037037037e-05,
|
259 |
+
"loss": 0.7857,
|
260 |
+
"step": 68
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.4,
|
264 |
+
"grad_norm": 5.370303153991699,
|
265 |
+
"learning_rate": 2.962962962962963e-05,
|
266 |
+
"loss": 0.5537,
|
267 |
+
"step": 70
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 1.44,
|
271 |
+
"grad_norm": 4.6746296882629395,
|
272 |
+
"learning_rate": 2.8888888888888888e-05,
|
273 |
+
"loss": 0.5636,
|
274 |
+
"step": 72
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 1.48,
|
278 |
+
"grad_norm": 5.238672733306885,
|
279 |
+
"learning_rate": 2.814814814814815e-05,
|
280 |
+
"loss": 0.5311,
|
281 |
+
"step": 74
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.52,
|
285 |
+
"grad_norm": 4.931227207183838,
|
286 |
+
"learning_rate": 2.7407407407407408e-05,
|
287 |
+
"loss": 0.5448,
|
288 |
+
"step": 76
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 1.56,
|
292 |
+
"grad_norm": 13.78615665435791,
|
293 |
+
"learning_rate": 2.6666666666666667e-05,
|
294 |
+
"loss": 0.6089,
|
295 |
+
"step": 78
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 1.6,
|
299 |
+
"grad_norm": 4.783405303955078,
|
300 |
+
"learning_rate": 2.5925925925925925e-05,
|
301 |
+
"loss": 0.422,
|
302 |
+
"step": 80
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.6400000000000001,
|
306 |
+
"grad_norm": 10.756999969482422,
|
307 |
+
"learning_rate": 2.5185185185185183e-05,
|
308 |
+
"loss": 0.5627,
|
309 |
+
"step": 82
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 1.6800000000000002,
|
313 |
+
"grad_norm": 8.377484321594238,
|
314 |
+
"learning_rate": 2.4444444444444445e-05,
|
315 |
+
"loss": 0.6638,
|
316 |
+
"step": 84
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 1.72,
|
320 |
+
"grad_norm": 6.980154991149902,
|
321 |
+
"learning_rate": 2.3703703703703707e-05,
|
322 |
+
"loss": 0.7009,
|
323 |
+
"step": 86
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 1.76,
|
327 |
+
"grad_norm": 5.8498334884643555,
|
328 |
+
"learning_rate": 2.2962962962962965e-05,
|
329 |
+
"loss": 0.419,
|
330 |
+
"step": 88
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 1.8,
|
334 |
+
"grad_norm": 7.8378520011901855,
|
335 |
+
"learning_rate": 2.2222222222222223e-05,
|
336 |
+
"loss": 0.4252,
|
337 |
+
"step": 90
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 1.8399999999999999,
|
341 |
+
"grad_norm": 8.54397201538086,
|
342 |
+
"learning_rate": 2.148148148148148e-05,
|
343 |
+
"loss": 0.425,
|
344 |
+
"step": 92
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.88,
|
348 |
+
"grad_norm": 9.064745903015137,
|
349 |
+
"learning_rate": 2.074074074074074e-05,
|
350 |
+
"loss": 0.5294,
|
351 |
+
"step": 94
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 1.92,
|
355 |
+
"grad_norm": 10.862845420837402,
|
356 |
+
"learning_rate": 2e-05,
|
357 |
+
"loss": 0.9176,
|
358 |
+
"step": 96
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 1.96,
|
362 |
+
"grad_norm": 6.8356475830078125,
|
363 |
+
"learning_rate": 1.925925925925926e-05,
|
364 |
+
"loss": 0.433,
|
365 |
+
"step": 98
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 2.0,
|
369 |
+
"grad_norm": 4.982166290283203,
|
370 |
+
"learning_rate": 1.8518518518518518e-05,
|
371 |
+
"loss": 0.5614,
|
372 |
+
"step": 100
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 2.0,
|
376 |
+
"eval_accuracy": 0.69,
|
377 |
+
"eval_auc": 0.8136,
|
378 |
+
"eval_f1": 0.6265060240963856,
|
379 |
+
"eval_loss": 0.5809483528137207,
|
380 |
+
"eval_precision": 0.7878787878787878,
|
381 |
+
"eval_recall": 0.52,
|
382 |
+
"eval_runtime": 16.0696,
|
383 |
+
"eval_samples_per_second": 6.223,
|
384 |
+
"eval_steps_per_second": 0.436,
|
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": 52622211072000.0,
|
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 sha256:37822338eb51765954dd0676f088f360bfb0448fcb392a7da5982c57d8f4768a
|
3 |
+
size 5048
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "0",
|
15 |
+
"1": "1"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"0": 0,
|
21 |
+
"1": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "bert",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.40.1",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 30522
|
36 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fd255e3b9cc12c5fe17d59cff701cb1c35b26f77581d23182af7f7a66af07a5
|
3 |
+
size 437958648
|
runs/May16_00-39-43_r-bjankav-neurips-bert-ixe8k41t-07e80-8p5jg/events.out.tfevents.1715819983.r-bjankav-neurips-bert-ixe8k41t-07e80-8p5jg.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 sha256:1e00fdb5125b19267552c04e8738bde9f14b5bcdc14fa43c0c16abf7ddfa9425
|
3 |
+
size 22297
|
runs/May16_00-39-43_r-bjankav-neurips-bert-ixe8k41t-07e80-8p5jg/events.out.tfevents.1715820781.r-bjankav-neurips-bert-ixe8k41t-07e80-8p5jg.87.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5f0f295bb85f909ad84da7390af6b4c3b2a75bf894359a004254dab572ea0db
|
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": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37822338eb51765954dd0676f088f360bfb0448fcb392a7da5982c57d8f4768a
|
3 |
+
size 5048
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "neurips-bert-combined1/autotrain-data",
|
3 |
+
"model": "google-bert/bert-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-combined1",
|
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
|
|