syarulzaffi commited on
Commit
d733398
·
verified ·
1 Parent(s): fc9c7ac

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - text-classification
6
+ base_model: distilbert/distilbert-base-uncased-finetuned-sst-2-english
7
+ widget:
8
+ - text: "I love AutoTrain"
9
+ ---
10
+
11
+ # Model Trained Using AutoTrain
12
+
13
+ - Problem type: Text Classification
14
+
15
+ ## Validation Metrics
16
+ loss: 3.840347199002281e-05
17
+
18
+ f1_macro: 1.0
19
+
20
+ f1_micro: 1.0
21
+
22
+ f1_weighted: 1.0
23
+
24
+ precision_macro: 1.0
25
+
26
+ precision_micro: 1.0
27
+
28
+ precision_weighted: 1.0
29
+
30
+ recall_macro: 1.0
31
+
32
+ recall_micro: 1.0
33
+
34
+ recall_weighted: 1.0
35
+
36
+ accuracy: 1.0
checkpoint-3750/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased-finetuned-sst-2-english",
3
+ "_num_labels": 7,
4
+ "activation": "gelu",
5
+ "architectures": [
6
+ "DistilBertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "dim": 768,
10
+ "dropout": 0.1,
11
+ "finetuning_task": "sst-2",
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "%Y-%m-%d",
15
+ "1": "%Y-%m-%d %H:%M:%S %Z",
16
+ "2": "%Y-%m-%dT%H:%M:%S",
17
+ "3": "%Y-%m-%dT%H:%M:%SZ",
18
+ "4": "%a, %d %b %Y",
19
+ "5": "%d/%m/%Y",
20
+ "6": "%m-%d-%Y %H:%M"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "label2id": {
24
+ "%Y-%m-%d": 0,
25
+ "%Y-%m-%d %H:%M:%S %Z": 1,
26
+ "%Y-%m-%dT%H:%M:%S": 2,
27
+ "%Y-%m-%dT%H:%M:%SZ": 3,
28
+ "%a, %d %b %Y": 4,
29
+ "%d/%m/%Y": 5,
30
+ "%m-%d-%Y %H:%M": 6
31
+ },
32
+ "max_position_embeddings": 512,
33
+ "model_type": "distilbert",
34
+ "n_heads": 12,
35
+ "n_layers": 6,
36
+ "output_past": true,
37
+ "pad_token_id": 0,
38
+ "problem_type": "single_label_classification",
39
+ "qa_dropout": 0.1,
40
+ "seq_classif_dropout": 0.2,
41
+ "sinusoidal_pos_embds": false,
42
+ "tie_weights_": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.45.0",
45
+ "vocab_size": 30522
46
+ }
checkpoint-3750/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1dc46c4162db5128e0ad9e9ec3902d82b03b12a42a994ff18b79b6d5d8c01a3
3
+ size 267847948
checkpoint-3750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:221164600913c6da9efca714c2b468f789e9659d58080be0254f7bc113c808ef
3
+ size 535755130
checkpoint-3750/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0953e3b16d6a78e1bbdaadff29153fe7a99e41cb6e295d26ecfd165d9c11d8d
3
+ size 13990
checkpoint-3750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed373512d200bc7dc4bb45ca208be38a790a2df64913959820c21a83640bcaf9
3
+ size 1064
checkpoint-3750/trainer_state.json ADDED
@@ -0,0 +1,1146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.840347199002281e-05,
3
+ "best_model_checkpoint": "autotrain-7uf55-m0z0j/checkpoint-3750",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3750,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "grad_norm": 4.304464340209961,
14
+ "learning_rate": 3.3333333333333333e-06,
15
+ "loss": 1.9314,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.04,
20
+ "grad_norm": 4.920653343200684,
21
+ "learning_rate": 6.666666666666667e-06,
22
+ "loss": 1.817,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.06,
27
+ "grad_norm": 6.059542655944824,
28
+ "learning_rate": 1e-05,
29
+ "loss": 1.5561,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.08,
34
+ "grad_norm": 9.400043487548828,
35
+ "learning_rate": 1.3333333333333333e-05,
36
+ "loss": 1.1842,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.1,
41
+ "grad_norm": 4.524064540863037,
42
+ "learning_rate": 1.6666666666666667e-05,
43
+ "loss": 0.7135,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.12,
48
+ "grad_norm": 2.0720291137695312,
49
+ "learning_rate": 2e-05,
50
+ "loss": 0.3595,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.14,
55
+ "grad_norm": 0.7319427728652954,
56
+ "learning_rate": 2.3333333333333336e-05,
57
+ "loss": 0.1482,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.16,
62
+ "grad_norm": 0.31106308102607727,
63
+ "learning_rate": 2.6666666666666667e-05,
64
+ "loss": 0.0588,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.18,
69
+ "grad_norm": 0.25692152976989746,
70
+ "learning_rate": 3e-05,
71
+ "loss": 0.0303,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.2,
76
+ "grad_norm": 0.14743871986865997,
77
+ "learning_rate": 3.3333333333333335e-05,
78
+ "loss": 0.0197,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.22,
83
+ "grad_norm": 0.12044914811849594,
84
+ "learning_rate": 3.6666666666666666e-05,
85
+ "loss": 0.0137,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.24,
90
+ "grad_norm": 0.10430993139743805,
91
+ "learning_rate": 4e-05,
92
+ "loss": 0.0103,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.26,
97
+ "grad_norm": 0.07196471840143204,
98
+ "learning_rate": 4.3333333333333334e-05,
99
+ "loss": 0.0083,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.28,
104
+ "grad_norm": 0.060800701379776,
105
+ "learning_rate": 4.666666666666667e-05,
106
+ "loss": 0.0066,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.3,
111
+ "grad_norm": 0.043456610292196274,
112
+ "learning_rate": 5e-05,
113
+ "loss": 0.005,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.32,
118
+ "grad_norm": 0.057310353964567184,
119
+ "learning_rate": 4.962962962962963e-05,
120
+ "loss": 0.0043,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.34,
125
+ "grad_norm": 0.037824537605047226,
126
+ "learning_rate": 4.925925925925926e-05,
127
+ "loss": 0.0034,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.36,
132
+ "grad_norm": 0.034279532730579376,
133
+ "learning_rate": 4.888888888888889e-05,
134
+ "loss": 0.003,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.38,
139
+ "grad_norm": 0.0275254063308239,
140
+ "learning_rate": 4.851851851851852e-05,
141
+ "loss": 0.0025,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.4,
146
+ "grad_norm": 0.02090919390320778,
147
+ "learning_rate": 4.814814814814815e-05,
148
+ "loss": 0.0023,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.42,
153
+ "grad_norm": 0.0253460593521595,
154
+ "learning_rate": 4.7777777777777784e-05,
155
+ "loss": 0.0022,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.44,
160
+ "grad_norm": 0.023784471675753593,
161
+ "learning_rate": 4.740740740740741e-05,
162
+ "loss": 0.0019,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.46,
167
+ "grad_norm": 0.0204653088003397,
168
+ "learning_rate": 4.703703703703704e-05,
169
+ "loss": 0.0016,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.48,
174
+ "grad_norm": 0.017939284443855286,
175
+ "learning_rate": 4.666666666666667e-05,
176
+ "loss": 0.0015,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.5,
181
+ "grad_norm": 0.016193848103284836,
182
+ "learning_rate": 4.62962962962963e-05,
183
+ "loss": 0.0014,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.52,
188
+ "grad_norm": 0.015551267191767693,
189
+ "learning_rate": 4.592592592592593e-05,
190
+ "loss": 0.0013,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.54,
195
+ "grad_norm": 0.01420588232576847,
196
+ "learning_rate": 4.555555555555556e-05,
197
+ "loss": 0.0012,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.56,
202
+ "grad_norm": 0.01292155496776104,
203
+ "learning_rate": 4.518518518518519e-05,
204
+ "loss": 0.0011,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 0.58,
209
+ "grad_norm": 0.013550491072237492,
210
+ "learning_rate": 4.481481481481482e-05,
211
+ "loss": 0.001,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 0.6,
216
+ "grad_norm": 0.009992895647883415,
217
+ "learning_rate": 4.4444444444444447e-05,
218
+ "loss": 0.001,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 0.62,
223
+ "grad_norm": 0.010535758920013905,
224
+ "learning_rate": 4.4074074074074076e-05,
225
+ "loss": 0.0009,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 0.64,
230
+ "grad_norm": 0.010647440329194069,
231
+ "learning_rate": 4.3703703703703705e-05,
232
+ "loss": 0.0008,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 0.66,
237
+ "grad_norm": 0.008126591332256794,
238
+ "learning_rate": 4.3333333333333334e-05,
239
+ "loss": 0.0008,
240
+ "step": 825
241
+ },
242
+ {
243
+ "epoch": 0.68,
244
+ "grad_norm": 0.011784318834543228,
245
+ "learning_rate": 4.296296296296296e-05,
246
+ "loss": 0.0007,
247
+ "step": 850
248
+ },
249
+ {
250
+ "epoch": 0.7,
251
+ "grad_norm": 0.008342107757925987,
252
+ "learning_rate": 4.259259259259259e-05,
253
+ "loss": 0.0007,
254
+ "step": 875
255
+ },
256
+ {
257
+ "epoch": 0.72,
258
+ "grad_norm": 0.011928070336580276,
259
+ "learning_rate": 4.222222222222222e-05,
260
+ "loss": 0.0006,
261
+ "step": 900
262
+ },
263
+ {
264
+ "epoch": 0.74,
265
+ "grad_norm": 0.00867882277816534,
266
+ "learning_rate": 4.185185185185185e-05,
267
+ "loss": 0.0006,
268
+ "step": 925
269
+ },
270
+ {
271
+ "epoch": 0.76,
272
+ "grad_norm": 0.008829472586512566,
273
+ "learning_rate": 4.148148148148148e-05,
274
+ "loss": 0.0006,
275
+ "step": 950
276
+ },
277
+ {
278
+ "epoch": 0.78,
279
+ "grad_norm": 0.007913686335086823,
280
+ "learning_rate": 4.111111111111111e-05,
281
+ "loss": 0.0006,
282
+ "step": 975
283
+ },
284
+ {
285
+ "epoch": 0.8,
286
+ "grad_norm": 0.007089868187904358,
287
+ "learning_rate": 4.074074074074074e-05,
288
+ "loss": 0.0005,
289
+ "step": 1000
290
+ },
291
+ {
292
+ "epoch": 0.82,
293
+ "grad_norm": 0.005340853706002235,
294
+ "learning_rate": 4.0370370370370374e-05,
295
+ "loss": 0.0005,
296
+ "step": 1025
297
+ },
298
+ {
299
+ "epoch": 0.84,
300
+ "grad_norm": 0.006341038271784782,
301
+ "learning_rate": 4e-05,
302
+ "loss": 0.0005,
303
+ "step": 1050
304
+ },
305
+ {
306
+ "epoch": 0.86,
307
+ "grad_norm": 0.00493874866515398,
308
+ "learning_rate": 3.962962962962963e-05,
309
+ "loss": 0.0005,
310
+ "step": 1075
311
+ },
312
+ {
313
+ "epoch": 0.88,
314
+ "grad_norm": 0.00893533043563366,
315
+ "learning_rate": 3.925925925925926e-05,
316
+ "loss": 0.0004,
317
+ "step": 1100
318
+ },
319
+ {
320
+ "epoch": 0.9,
321
+ "grad_norm": 0.005718824919313192,
322
+ "learning_rate": 3.888888888888889e-05,
323
+ "loss": 0.0004,
324
+ "step": 1125
325
+ },
326
+ {
327
+ "epoch": 0.92,
328
+ "grad_norm": 0.0058049545623362064,
329
+ "learning_rate": 3.851851851851852e-05,
330
+ "loss": 0.0004,
331
+ "step": 1150
332
+ },
333
+ {
334
+ "epoch": 0.94,
335
+ "grad_norm": 0.004717515781521797,
336
+ "learning_rate": 3.814814814814815e-05,
337
+ "loss": 0.0004,
338
+ "step": 1175
339
+ },
340
+ {
341
+ "epoch": 0.96,
342
+ "grad_norm": 0.005214130040258169,
343
+ "learning_rate": 3.777777777777778e-05,
344
+ "loss": 0.0004,
345
+ "step": 1200
346
+ },
347
+ {
348
+ "epoch": 0.98,
349
+ "grad_norm": 0.005639470182359219,
350
+ "learning_rate": 3.740740740740741e-05,
351
+ "loss": 0.0004,
352
+ "step": 1225
353
+ },
354
+ {
355
+ "epoch": 1.0,
356
+ "grad_norm": 0.006479472853243351,
357
+ "learning_rate": 3.7037037037037037e-05,
358
+ "loss": 0.0004,
359
+ "step": 1250
360
+ },
361
+ {
362
+ "epoch": 1.0,
363
+ "eval_accuracy": 1.0,
364
+ "eval_f1_macro": 1.0,
365
+ "eval_f1_micro": 1.0,
366
+ "eval_f1_weighted": 1.0,
367
+ "eval_loss": 0.000196128647075966,
368
+ "eval_precision_macro": 1.0,
369
+ "eval_precision_micro": 1.0,
370
+ "eval_precision_weighted": 1.0,
371
+ "eval_recall_macro": 1.0,
372
+ "eval_recall_micro": 1.0,
373
+ "eval_recall_weighted": 1.0,
374
+ "eval_runtime": 96.7459,
375
+ "eval_samples_per_second": 10.336,
376
+ "eval_steps_per_second": 0.651,
377
+ "step": 1250
378
+ },
379
+ {
380
+ "epoch": 1.02,
381
+ "grad_norm": 0.0031228128354996443,
382
+ "learning_rate": 3.6666666666666666e-05,
383
+ "loss": 0.0003,
384
+ "step": 1275
385
+ },
386
+ {
387
+ "epoch": 1.04,
388
+ "grad_norm": 0.0036842897534370422,
389
+ "learning_rate": 3.62962962962963e-05,
390
+ "loss": 0.0003,
391
+ "step": 1300
392
+ },
393
+ {
394
+ "epoch": 1.06,
395
+ "grad_norm": 0.0037028491497039795,
396
+ "learning_rate": 3.592592592592593e-05,
397
+ "loss": 0.0003,
398
+ "step": 1325
399
+ },
400
+ {
401
+ "epoch": 1.08,
402
+ "grad_norm": 0.004495515022426844,
403
+ "learning_rate": 3.555555555555556e-05,
404
+ "loss": 0.0003,
405
+ "step": 1350
406
+ },
407
+ {
408
+ "epoch": 1.1,
409
+ "grad_norm": 0.004389617592096329,
410
+ "learning_rate": 3.518518518518519e-05,
411
+ "loss": 0.0003,
412
+ "step": 1375
413
+ },
414
+ {
415
+ "epoch": 1.12,
416
+ "grad_norm": 0.0040401131846010685,
417
+ "learning_rate": 3.481481481481482e-05,
418
+ "loss": 0.0003,
419
+ "step": 1400
420
+ },
421
+ {
422
+ "epoch": 1.1400000000000001,
423
+ "grad_norm": 0.0035321260802447796,
424
+ "learning_rate": 3.444444444444445e-05,
425
+ "loss": 0.0003,
426
+ "step": 1425
427
+ },
428
+ {
429
+ "epoch": 1.16,
430
+ "grad_norm": 0.007934887893497944,
431
+ "learning_rate": 3.4074074074074077e-05,
432
+ "loss": 0.0003,
433
+ "step": 1450
434
+ },
435
+ {
436
+ "epoch": 1.18,
437
+ "grad_norm": 0.004385160747915506,
438
+ "learning_rate": 3.3703703703703706e-05,
439
+ "loss": 0.0003,
440
+ "step": 1475
441
+ },
442
+ {
443
+ "epoch": 1.2,
444
+ "grad_norm": 0.003952551167458296,
445
+ "learning_rate": 3.3333333333333335e-05,
446
+ "loss": 0.0003,
447
+ "step": 1500
448
+ },
449
+ {
450
+ "epoch": 1.22,
451
+ "grad_norm": 0.0038910023868083954,
452
+ "learning_rate": 3.2962962962962964e-05,
453
+ "loss": 0.0002,
454
+ "step": 1525
455
+ },
456
+ {
457
+ "epoch": 1.24,
458
+ "grad_norm": 0.005208250600844622,
459
+ "learning_rate": 3.25925925925926e-05,
460
+ "loss": 0.0002,
461
+ "step": 1550
462
+ },
463
+ {
464
+ "epoch": 1.26,
465
+ "grad_norm": 0.003550452645868063,
466
+ "learning_rate": 3.222222222222223e-05,
467
+ "loss": 0.0002,
468
+ "step": 1575
469
+ },
470
+ {
471
+ "epoch": 1.28,
472
+ "grad_norm": 0.0026670030783861876,
473
+ "learning_rate": 3.185185185185185e-05,
474
+ "loss": 0.0002,
475
+ "step": 1600
476
+ },
477
+ {
478
+ "epoch": 1.3,
479
+ "grad_norm": 0.002486367477104068,
480
+ "learning_rate": 3.148148148148148e-05,
481
+ "loss": 0.0002,
482
+ "step": 1625
483
+ },
484
+ {
485
+ "epoch": 1.32,
486
+ "grad_norm": 0.0025664418935775757,
487
+ "learning_rate": 3.111111111111111e-05,
488
+ "loss": 0.0002,
489
+ "step": 1650
490
+ },
491
+ {
492
+ "epoch": 1.34,
493
+ "grad_norm": 0.003432709723711014,
494
+ "learning_rate": 3.074074074074074e-05,
495
+ "loss": 0.0002,
496
+ "step": 1675
497
+ },
498
+ {
499
+ "epoch": 1.3599999999999999,
500
+ "grad_norm": 0.003789544105529785,
501
+ "learning_rate": 3.037037037037037e-05,
502
+ "loss": 0.0002,
503
+ "step": 1700
504
+ },
505
+ {
506
+ "epoch": 1.38,
507
+ "grad_norm": 0.002509128535166383,
508
+ "learning_rate": 3e-05,
509
+ "loss": 0.0002,
510
+ "step": 1725
511
+ },
512
+ {
513
+ "epoch": 1.4,
514
+ "grad_norm": 0.0041717709973454475,
515
+ "learning_rate": 2.962962962962963e-05,
516
+ "loss": 0.0002,
517
+ "step": 1750
518
+ },
519
+ {
520
+ "epoch": 1.42,
521
+ "grad_norm": 0.0029575435910373926,
522
+ "learning_rate": 2.925925925925926e-05,
523
+ "loss": 0.0002,
524
+ "step": 1775
525
+ },
526
+ {
527
+ "epoch": 1.44,
528
+ "grad_norm": 0.0025973827578127384,
529
+ "learning_rate": 2.8888888888888888e-05,
530
+ "loss": 0.0002,
531
+ "step": 1800
532
+ },
533
+ {
534
+ "epoch": 1.46,
535
+ "grad_norm": 0.0026980151887983084,
536
+ "learning_rate": 2.851851851851852e-05,
537
+ "loss": 0.0002,
538
+ "step": 1825
539
+ },
540
+ {
541
+ "epoch": 1.48,
542
+ "grad_norm": 0.001652281265705824,
543
+ "learning_rate": 2.814814814814815e-05,
544
+ "loss": 0.0002,
545
+ "step": 1850
546
+ },
547
+ {
548
+ "epoch": 1.5,
549
+ "grad_norm": 0.003795761615037918,
550
+ "learning_rate": 2.777777777777778e-05,
551
+ "loss": 0.0002,
552
+ "step": 1875
553
+ },
554
+ {
555
+ "epoch": 1.52,
556
+ "grad_norm": 0.0022721276618540287,
557
+ "learning_rate": 2.7407407407407408e-05,
558
+ "loss": 0.0002,
559
+ "step": 1900
560
+ },
561
+ {
562
+ "epoch": 1.54,
563
+ "grad_norm": 0.0031409296207129955,
564
+ "learning_rate": 2.7037037037037037e-05,
565
+ "loss": 0.0002,
566
+ "step": 1925
567
+ },
568
+ {
569
+ "epoch": 1.56,
570
+ "grad_norm": 0.0019745349418371916,
571
+ "learning_rate": 2.6666666666666667e-05,
572
+ "loss": 0.0002,
573
+ "step": 1950
574
+ },
575
+ {
576
+ "epoch": 1.58,
577
+ "grad_norm": 0.003191662020981312,
578
+ "learning_rate": 2.6296296296296296e-05,
579
+ "loss": 0.0002,
580
+ "step": 1975
581
+ },
582
+ {
583
+ "epoch": 1.6,
584
+ "grad_norm": 0.0019591045565903187,
585
+ "learning_rate": 2.5925925925925925e-05,
586
+ "loss": 0.0002,
587
+ "step": 2000
588
+ },
589
+ {
590
+ "epoch": 1.62,
591
+ "grad_norm": 0.0021969389636069536,
592
+ "learning_rate": 2.5555555555555554e-05,
593
+ "loss": 0.0002,
594
+ "step": 2025
595
+ },
596
+ {
597
+ "epoch": 1.6400000000000001,
598
+ "grad_norm": 0.0018133741104975343,
599
+ "learning_rate": 2.5185185185185183e-05,
600
+ "loss": 0.0001,
601
+ "step": 2050
602
+ },
603
+ {
604
+ "epoch": 1.6600000000000001,
605
+ "grad_norm": 0.001964360475540161,
606
+ "learning_rate": 2.4814814814814816e-05,
607
+ "loss": 0.0001,
608
+ "step": 2075
609
+ },
610
+ {
611
+ "epoch": 1.6800000000000002,
612
+ "grad_norm": 0.001756583689711988,
613
+ "learning_rate": 2.4444444444444445e-05,
614
+ "loss": 0.0001,
615
+ "step": 2100
616
+ },
617
+ {
618
+ "epoch": 1.7,
619
+ "grad_norm": 0.001773927011527121,
620
+ "learning_rate": 2.4074074074074074e-05,
621
+ "loss": 0.0001,
622
+ "step": 2125
623
+ },
624
+ {
625
+ "epoch": 1.72,
626
+ "grad_norm": 0.0019142563687637448,
627
+ "learning_rate": 2.3703703703703707e-05,
628
+ "loss": 0.0001,
629
+ "step": 2150
630
+ },
631
+ {
632
+ "epoch": 1.74,
633
+ "grad_norm": 0.002117906929925084,
634
+ "learning_rate": 2.3333333333333336e-05,
635
+ "loss": 0.0001,
636
+ "step": 2175
637
+ },
638
+ {
639
+ "epoch": 1.76,
640
+ "grad_norm": 0.0019606170244514942,
641
+ "learning_rate": 2.2962962962962965e-05,
642
+ "loss": 0.0001,
643
+ "step": 2200
644
+ },
645
+ {
646
+ "epoch": 1.78,
647
+ "grad_norm": 0.001559660886414349,
648
+ "learning_rate": 2.2592592592592594e-05,
649
+ "loss": 0.0001,
650
+ "step": 2225
651
+ },
652
+ {
653
+ "epoch": 1.8,
654
+ "grad_norm": 0.0015773209743201733,
655
+ "learning_rate": 2.2222222222222223e-05,
656
+ "loss": 0.0001,
657
+ "step": 2250
658
+ },
659
+ {
660
+ "epoch": 1.8199999999999998,
661
+ "grad_norm": 0.002937556942924857,
662
+ "learning_rate": 2.1851851851851852e-05,
663
+ "loss": 0.0001,
664
+ "step": 2275
665
+ },
666
+ {
667
+ "epoch": 1.8399999999999999,
668
+ "grad_norm": 0.0017125752056017518,
669
+ "learning_rate": 2.148148148148148e-05,
670
+ "loss": 0.0001,
671
+ "step": 2300
672
+ },
673
+ {
674
+ "epoch": 1.8599999999999999,
675
+ "grad_norm": 0.0016449954127892852,
676
+ "learning_rate": 2.111111111111111e-05,
677
+ "loss": 0.0001,
678
+ "step": 2325
679
+ },
680
+ {
681
+ "epoch": 1.88,
682
+ "grad_norm": 0.0019681367557495832,
683
+ "learning_rate": 2.074074074074074e-05,
684
+ "loss": 0.0001,
685
+ "step": 2350
686
+ },
687
+ {
688
+ "epoch": 1.9,
689
+ "grad_norm": 0.0017161853611469269,
690
+ "learning_rate": 2.037037037037037e-05,
691
+ "loss": 0.0001,
692
+ "step": 2375
693
+ },
694
+ {
695
+ "epoch": 1.92,
696
+ "grad_norm": 0.0017810638528317213,
697
+ "learning_rate": 2e-05,
698
+ "loss": 0.0001,
699
+ "step": 2400
700
+ },
701
+ {
702
+ "epoch": 1.94,
703
+ "grad_norm": 0.001222253660671413,
704
+ "learning_rate": 1.962962962962963e-05,
705
+ "loss": 0.0001,
706
+ "step": 2425
707
+ },
708
+ {
709
+ "epoch": 1.96,
710
+ "grad_norm": 0.001496514305472374,
711
+ "learning_rate": 1.925925925925926e-05,
712
+ "loss": 0.0001,
713
+ "step": 2450
714
+ },
715
+ {
716
+ "epoch": 1.98,
717
+ "grad_norm": 0.0015075966948643327,
718
+ "learning_rate": 1.888888888888889e-05,
719
+ "loss": 0.0001,
720
+ "step": 2475
721
+ },
722
+ {
723
+ "epoch": 2.0,
724
+ "grad_norm": 0.001401808112859726,
725
+ "learning_rate": 1.8518518518518518e-05,
726
+ "loss": 0.0001,
727
+ "step": 2500
728
+ },
729
+ {
730
+ "epoch": 2.0,
731
+ "eval_accuracy": 1.0,
732
+ "eval_f1_macro": 1.0,
733
+ "eval_f1_micro": 1.0,
734
+ "eval_f1_weighted": 1.0,
735
+ "eval_loss": 5.750094715040177e-05,
736
+ "eval_precision_macro": 1.0,
737
+ "eval_precision_micro": 1.0,
738
+ "eval_precision_weighted": 1.0,
739
+ "eval_recall_macro": 1.0,
740
+ "eval_recall_micro": 1.0,
741
+ "eval_recall_weighted": 1.0,
742
+ "eval_runtime": 101.3091,
743
+ "eval_samples_per_second": 9.871,
744
+ "eval_steps_per_second": 0.622,
745
+ "step": 2500
746
+ },
747
+ {
748
+ "epoch": 2.02,
749
+ "grad_norm": 0.002077981363981962,
750
+ "learning_rate": 1.814814814814815e-05,
751
+ "loss": 0.0001,
752
+ "step": 2525
753
+ },
754
+ {
755
+ "epoch": 2.04,
756
+ "grad_norm": 0.0016811484238132834,
757
+ "learning_rate": 1.777777777777778e-05,
758
+ "loss": 0.0001,
759
+ "step": 2550
760
+ },
761
+ {
762
+ "epoch": 2.06,
763
+ "grad_norm": 0.00154784822370857,
764
+ "learning_rate": 1.740740740740741e-05,
765
+ "loss": 0.0001,
766
+ "step": 2575
767
+ },
768
+ {
769
+ "epoch": 2.08,
770
+ "grad_norm": 0.00146737031172961,
771
+ "learning_rate": 1.7037037037037038e-05,
772
+ "loss": 0.0001,
773
+ "step": 2600
774
+ },
775
+ {
776
+ "epoch": 2.1,
777
+ "grad_norm": 0.0012567444937303662,
778
+ "learning_rate": 1.6666666666666667e-05,
779
+ "loss": 0.0001,
780
+ "step": 2625
781
+ },
782
+ {
783
+ "epoch": 2.12,
784
+ "grad_norm": 0.001397090614773333,
785
+ "learning_rate": 1.62962962962963e-05,
786
+ "loss": 0.0001,
787
+ "step": 2650
788
+ },
789
+ {
790
+ "epoch": 2.14,
791
+ "grad_norm": 0.0014192495727911592,
792
+ "learning_rate": 1.5925925925925926e-05,
793
+ "loss": 0.0001,
794
+ "step": 2675
795
+ },
796
+ {
797
+ "epoch": 2.16,
798
+ "grad_norm": 0.0014421796659007668,
799
+ "learning_rate": 1.5555555555555555e-05,
800
+ "loss": 0.0001,
801
+ "step": 2700
802
+ },
803
+ {
804
+ "epoch": 2.18,
805
+ "grad_norm": 0.00168473063968122,
806
+ "learning_rate": 1.5185185185185186e-05,
807
+ "loss": 0.0001,
808
+ "step": 2725
809
+ },
810
+ {
811
+ "epoch": 2.2,
812
+ "grad_norm": 0.0013392771361395717,
813
+ "learning_rate": 1.4814814814814815e-05,
814
+ "loss": 0.0001,
815
+ "step": 2750
816
+ },
817
+ {
818
+ "epoch": 2.22,
819
+ "grad_norm": 0.0011290446855127811,
820
+ "learning_rate": 1.4444444444444444e-05,
821
+ "loss": 0.0001,
822
+ "step": 2775
823
+ },
824
+ {
825
+ "epoch": 2.24,
826
+ "grad_norm": 0.001582424738444388,
827
+ "learning_rate": 1.4074074074074075e-05,
828
+ "loss": 0.0001,
829
+ "step": 2800
830
+ },
831
+ {
832
+ "epoch": 2.26,
833
+ "grad_norm": 0.0016395584680140018,
834
+ "learning_rate": 1.3703703703703704e-05,
835
+ "loss": 0.0001,
836
+ "step": 2825
837
+ },
838
+ {
839
+ "epoch": 2.2800000000000002,
840
+ "grad_norm": 0.0009652812150307,
841
+ "learning_rate": 1.3333333333333333e-05,
842
+ "loss": 0.0001,
843
+ "step": 2850
844
+ },
845
+ {
846
+ "epoch": 2.3,
847
+ "grad_norm": 0.001358719659037888,
848
+ "learning_rate": 1.2962962962962962e-05,
849
+ "loss": 0.0001,
850
+ "step": 2875
851
+ },
852
+ {
853
+ "epoch": 2.32,
854
+ "grad_norm": 0.0015577167505398393,
855
+ "learning_rate": 1.2592592592592592e-05,
856
+ "loss": 0.0001,
857
+ "step": 2900
858
+ },
859
+ {
860
+ "epoch": 2.34,
861
+ "grad_norm": 0.0012988918460905552,
862
+ "learning_rate": 1.2222222222222222e-05,
863
+ "loss": 0.0001,
864
+ "step": 2925
865
+ },
866
+ {
867
+ "epoch": 2.36,
868
+ "grad_norm": 0.0008892663172446191,
869
+ "learning_rate": 1.1851851851851853e-05,
870
+ "loss": 0.0001,
871
+ "step": 2950
872
+ },
873
+ {
874
+ "epoch": 2.38,
875
+ "grad_norm": 0.0012016637483611703,
876
+ "learning_rate": 1.1481481481481482e-05,
877
+ "loss": 0.0001,
878
+ "step": 2975
879
+ },
880
+ {
881
+ "epoch": 2.4,
882
+ "grad_norm": 0.0020903022959828377,
883
+ "learning_rate": 1.1111111111111112e-05,
884
+ "loss": 0.0001,
885
+ "step": 3000
886
+ },
887
+ {
888
+ "epoch": 2.42,
889
+ "grad_norm": 0.0015041292645037174,
890
+ "learning_rate": 1.074074074074074e-05,
891
+ "loss": 0.0001,
892
+ "step": 3025
893
+ },
894
+ {
895
+ "epoch": 2.44,
896
+ "grad_norm": 0.001461705076508224,
897
+ "learning_rate": 1.037037037037037e-05,
898
+ "loss": 0.0001,
899
+ "step": 3050
900
+ },
901
+ {
902
+ "epoch": 2.46,
903
+ "grad_norm": 0.0012131037656217813,
904
+ "learning_rate": 1e-05,
905
+ "loss": 0.0001,
906
+ "step": 3075
907
+ },
908
+ {
909
+ "epoch": 2.48,
910
+ "grad_norm": 0.0012345913564786315,
911
+ "learning_rate": 9.62962962962963e-06,
912
+ "loss": 0.0001,
913
+ "step": 3100
914
+ },
915
+ {
916
+ "epoch": 2.5,
917
+ "grad_norm": 0.0012430918868631124,
918
+ "learning_rate": 9.259259259259259e-06,
919
+ "loss": 0.0001,
920
+ "step": 3125
921
+ },
922
+ {
923
+ "epoch": 2.52,
924
+ "grad_norm": 0.0016790252411738038,
925
+ "learning_rate": 8.88888888888889e-06,
926
+ "loss": 0.0001,
927
+ "step": 3150
928
+ },
929
+ {
930
+ "epoch": 2.54,
931
+ "grad_norm": 0.0011509001487866044,
932
+ "learning_rate": 8.518518518518519e-06,
933
+ "loss": 0.0001,
934
+ "step": 3175
935
+ },
936
+ {
937
+ "epoch": 2.56,
938
+ "grad_norm": 0.0017348213586956263,
939
+ "learning_rate": 8.14814814814815e-06,
940
+ "loss": 0.0001,
941
+ "step": 3200
942
+ },
943
+ {
944
+ "epoch": 2.58,
945
+ "grad_norm": 0.0011379763018339872,
946
+ "learning_rate": 7.777777777777777e-06,
947
+ "loss": 0.0001,
948
+ "step": 3225
949
+ },
950
+ {
951
+ "epoch": 2.6,
952
+ "grad_norm": 0.0013867334928363562,
953
+ "learning_rate": 7.4074074074074075e-06,
954
+ "loss": 0.0001,
955
+ "step": 3250
956
+ },
957
+ {
958
+ "epoch": 2.62,
959
+ "grad_norm": 0.0012076362036168575,
960
+ "learning_rate": 7.0370370370370375e-06,
961
+ "loss": 0.0001,
962
+ "step": 3275
963
+ },
964
+ {
965
+ "epoch": 2.64,
966
+ "grad_norm": 0.0010235183872282505,
967
+ "learning_rate": 6.666666666666667e-06,
968
+ "loss": 0.0001,
969
+ "step": 3300
970
+ },
971
+ {
972
+ "epoch": 2.66,
973
+ "grad_norm": 0.001814654329791665,
974
+ "learning_rate": 6.296296296296296e-06,
975
+ "loss": 0.0001,
976
+ "step": 3325
977
+ },
978
+ {
979
+ "epoch": 2.68,
980
+ "grad_norm": 0.001351826242171228,
981
+ "learning_rate": 5.925925925925927e-06,
982
+ "loss": 0.0001,
983
+ "step": 3350
984
+ },
985
+ {
986
+ "epoch": 2.7,
987
+ "grad_norm": 0.0011372161097824574,
988
+ "learning_rate": 5.555555555555556e-06,
989
+ "loss": 0.0001,
990
+ "step": 3375
991
+ },
992
+ {
993
+ "epoch": 2.7199999999999998,
994
+ "grad_norm": 0.0016640841495245695,
995
+ "learning_rate": 5.185185185185185e-06,
996
+ "loss": 0.0001,
997
+ "step": 3400
998
+ },
999
+ {
1000
+ "epoch": 2.74,
1001
+ "grad_norm": 0.0012870054924860597,
1002
+ "learning_rate": 4.814814814814815e-06,
1003
+ "loss": 0.0001,
1004
+ "step": 3425
1005
+ },
1006
+ {
1007
+ "epoch": 2.76,
1008
+ "grad_norm": 0.001348846941255033,
1009
+ "learning_rate": 4.444444444444445e-06,
1010
+ "loss": 0.0001,
1011
+ "step": 3450
1012
+ },
1013
+ {
1014
+ "epoch": 2.7800000000000002,
1015
+ "grad_norm": 0.0008714779978618026,
1016
+ "learning_rate": 4.074074074074075e-06,
1017
+ "loss": 0.0001,
1018
+ "step": 3475
1019
+ },
1020
+ {
1021
+ "epoch": 2.8,
1022
+ "grad_norm": 0.0009024555329233408,
1023
+ "learning_rate": 3.7037037037037037e-06,
1024
+ "loss": 0.0001,
1025
+ "step": 3500
1026
+ },
1027
+ {
1028
+ "epoch": 2.82,
1029
+ "grad_norm": 0.0015532090328633785,
1030
+ "learning_rate": 3.3333333333333333e-06,
1031
+ "loss": 0.0001,
1032
+ "step": 3525
1033
+ },
1034
+ {
1035
+ "epoch": 2.84,
1036
+ "grad_norm": 0.0009049284853972495,
1037
+ "learning_rate": 2.9629629629629633e-06,
1038
+ "loss": 0.0001,
1039
+ "step": 3550
1040
+ },
1041
+ {
1042
+ "epoch": 2.86,
1043
+ "grad_norm": 0.0011410305742174387,
1044
+ "learning_rate": 2.5925925925925925e-06,
1045
+ "loss": 0.0001,
1046
+ "step": 3575
1047
+ },
1048
+ {
1049
+ "epoch": 2.88,
1050
+ "grad_norm": 0.0011191493831574917,
1051
+ "learning_rate": 2.2222222222222225e-06,
1052
+ "loss": 0.0001,
1053
+ "step": 3600
1054
+ },
1055
+ {
1056
+ "epoch": 2.9,
1057
+ "grad_norm": 0.001286625862121582,
1058
+ "learning_rate": 1.8518518518518519e-06,
1059
+ "loss": 0.0001,
1060
+ "step": 3625
1061
+ },
1062
+ {
1063
+ "epoch": 2.92,
1064
+ "grad_norm": 0.00163840944878757,
1065
+ "learning_rate": 1.4814814814814817e-06,
1066
+ "loss": 0.0001,
1067
+ "step": 3650
1068
+ },
1069
+ {
1070
+ "epoch": 2.94,
1071
+ "grad_norm": 0.0011437933426350355,
1072
+ "learning_rate": 1.1111111111111112e-06,
1073
+ "loss": 0.0001,
1074
+ "step": 3675
1075
+ },
1076
+ {
1077
+ "epoch": 2.96,
1078
+ "grad_norm": 0.0009327352163381875,
1079
+ "learning_rate": 7.407407407407408e-07,
1080
+ "loss": 0.0001,
1081
+ "step": 3700
1082
+ },
1083
+ {
1084
+ "epoch": 2.98,
1085
+ "grad_norm": 0.001205917214974761,
1086
+ "learning_rate": 3.703703703703704e-07,
1087
+ "loss": 0.0001,
1088
+ "step": 3725
1089
+ },
1090
+ {
1091
+ "epoch": 3.0,
1092
+ "grad_norm": 0.001018369453959167,
1093
+ "learning_rate": 0.0,
1094
+ "loss": 0.0001,
1095
+ "step": 3750
1096
+ },
1097
+ {
1098
+ "epoch": 3.0,
1099
+ "eval_accuracy": 1.0,
1100
+ "eval_f1_macro": 1.0,
1101
+ "eval_f1_micro": 1.0,
1102
+ "eval_f1_weighted": 1.0,
1103
+ "eval_loss": 3.840347199002281e-05,
1104
+ "eval_precision_macro": 1.0,
1105
+ "eval_precision_micro": 1.0,
1106
+ "eval_precision_weighted": 1.0,
1107
+ "eval_recall_macro": 1.0,
1108
+ "eval_recall_micro": 1.0,
1109
+ "eval_recall_weighted": 1.0,
1110
+ "eval_runtime": 108.195,
1111
+ "eval_samples_per_second": 9.243,
1112
+ "eval_steps_per_second": 0.582,
1113
+ "step": 3750
1114
+ }
1115
+ ],
1116
+ "logging_steps": 25,
1117
+ "max_steps": 3750,
1118
+ "num_input_tokens_seen": 0,
1119
+ "num_train_epochs": 3,
1120
+ "save_steps": 500,
1121
+ "stateful_callbacks": {
1122
+ "EarlyStoppingCallback": {
1123
+ "args": {
1124
+ "early_stopping_patience": 5,
1125
+ "early_stopping_threshold": 0.01
1126
+ },
1127
+ "attributes": {
1128
+ "early_stopping_patience_counter": 2
1129
+ }
1130
+ },
1131
+ "TrainerControl": {
1132
+ "args": {
1133
+ "should_epoch_stop": false,
1134
+ "should_evaluate": false,
1135
+ "should_log": false,
1136
+ "should_save": true,
1137
+ "should_training_stop": true
1138
+ },
1139
+ "attributes": {}
1140
+ }
1141
+ },
1142
+ "total_flos": 993594078720000.0,
1143
+ "train_batch_size": 8,
1144
+ "trial_name": null,
1145
+ "trial_params": null
1146
+ }
checkpoint-3750/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623ac3e718ddda2f509f78bcfde295d2ae64091542cfa2d818f59d08d13154f3
3
+ size 5240
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased-finetuned-sst-2-english",
3
+ "_num_labels": 7,
4
+ "activation": "gelu",
5
+ "architectures": [
6
+ "DistilBertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "dim": 768,
10
+ "dropout": 0.1,
11
+ "finetuning_task": "sst-2",
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "%Y-%m-%d",
15
+ "1": "%Y-%m-%d %H:%M:%S %Z",
16
+ "2": "%Y-%m-%dT%H:%M:%S",
17
+ "3": "%Y-%m-%dT%H:%M:%SZ",
18
+ "4": "%a, %d %b %Y",
19
+ "5": "%d/%m/%Y",
20
+ "6": "%m-%d-%Y %H:%M"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "label2id": {
24
+ "%Y-%m-%d": 0,
25
+ "%Y-%m-%d %H:%M:%S %Z": 1,
26
+ "%Y-%m-%dT%H:%M:%S": 2,
27
+ "%Y-%m-%dT%H:%M:%SZ": 3,
28
+ "%a, %d %b %Y": 4,
29
+ "%d/%m/%Y": 5,
30
+ "%m-%d-%Y %H:%M": 6
31
+ },
32
+ "max_position_embeddings": 512,
33
+ "model_type": "distilbert",
34
+ "n_heads": 12,
35
+ "n_layers": 6,
36
+ "output_past": true,
37
+ "pad_token_id": 0,
38
+ "problem_type": "single_label_classification",
39
+ "qa_dropout": 0.1,
40
+ "seq_classif_dropout": 0.2,
41
+ "sinusoidal_pos_embds": false,
42
+ "tie_weights_": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.45.0",
45
+ "vocab_size": 30522
46
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1dc46c4162db5128e0ad9e9ec3902d82b03b12a42a994ff18b79b6d5d8c01a3
3
+ size 267847948
runs/Oct31_17-10-20_r-syarulzaffi-space-8yelwaor-160c7-twr5k/events.out.tfevents.1730394621.r-syarulzaffi-space-8yelwaor-160c7-twr5k.107.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:325add46c02fc77467ade9bedc688778b5494137df4ab38ffedc654eabb1cd3d
3
- size 37828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0949ff46321a7a41f2aeb6aea22c9d79d4dcf7845769e1d64767d7659e5c93b4
3
+ size 39859
runs/Oct31_17-10-20_r-syarulzaffi-space-8yelwaor-160c7-twr5k/events.out.tfevents.1730407065.r-syarulzaffi-space-8yelwaor-160c7-twr5k.107.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cdff92bacd42f657dd39bb0c50b94f4ad5780a3c39fbb5aca93151922b45e4e
3
+ size 921
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623ac3e718ddda2f509f78bcfde295d2ae64091542cfa2d818f59d08d13154f3
3
+ size 5240
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-7uf55-m0z0j/autotrain-data",
3
+ "model": "distilbert/distilbert-base-uncased-finetuned-sst-2-english",
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": "autotrain-7uf55-m0z0j",
21
+ "auto_find_batch_size": false,
22
+ "mixed_precision": "none",
23
+ "save_total_limit": 1,
24
+ "push_to_hub": true,
25
+ "eval_strategy": "epoch",
26
+ "username": "syarulzaffi",
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