alohia commited on
Commit
d8a3609
1 Parent(s): 04f0ccd

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: finiteautomata/bertweet-base-sentiment-analysis
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: 0.021347366273403168
17
+
18
+ f1_macro: 0.9936121048770471
19
+
20
+ f1_micro: 0.9955175434076975
21
+
22
+ f1_weighted: 0.9955108152465474
23
+
24
+ precision_macro: 0.9946094746601329
25
+
26
+ precision_micro: 0.9955175434076975
27
+
28
+ precision_weighted: 0.9955142956474508
29
+
30
+ recall_macro: 0.9926308276207328
31
+
32
+ recall_micro: 0.9955175434076975
33
+
34
+ recall_weighted: 0.9955175434076975
35
+
36
+ accuracy: 0.9955175434076975
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3639/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "finiteautomata/bertweet-base-sentiment-analysis",
3
+ "_num_labels": 3,
4
+ "architectures": [
5
+ "RobertaForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "NEG",
17
+ "1": "NEU",
18
+ "2": "POS"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "NEG": 0,
24
+ "NEU": 1,
25
+ "POS": 2
26
+ },
27
+ "layer_norm_eps": 1e-05,
28
+ "max_position_embeddings": 130,
29
+ "model_type": "roberta",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "tokenizer_class": "BertweetTokenizer",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.45.0",
38
+ "type_vocab_size": 1,
39
+ "use_cache": true,
40
+ "vocab_size": 64001
41
+ }
checkpoint-3639/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec1a41015d1cbf6fb1eb310fdb119815bb0a7d46ffdb320e51a506efdced8254
3
+ size 539633244
checkpoint-3639/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf7475f1afdeec2ab10720b721a6814f0b57ec26029d122aa095c9a52675590d
3
+ size 1079386298
checkpoint-3639/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49f991389b462b37c74eaf89fea6be796a3c37607b1a8b83b9e07cda5d090328
3
+ size 14244
checkpoint-3639/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a852602f36fe1b62d8bce97a9d20037365f087660c663f6f969fe086190a57e
3
+ size 1064
checkpoint-3639/trainer_state.json ADDED
@@ -0,0 +1,1111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.021347366273403168,
3
+ "best_model_checkpoint": "autotrain-78oj2-jlrbv/checkpoint-3639",
4
+ "epoch": 2.99938182567484,
5
+ "eval_steps": 500,
6
+ "global_step": 3639,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0206058108386565,
13
+ "grad_norm": 5.651961326599121,
14
+ "learning_rate": 3.021978021978022e-06,
15
+ "loss": 0.9893,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.041211621677313,
20
+ "grad_norm": 3.856781005859375,
21
+ "learning_rate": 6.456043956043957e-06,
22
+ "loss": 0.8203,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.0618174325159695,
27
+ "grad_norm": 3.5703439712524414,
28
+ "learning_rate": 9.89010989010989e-06,
29
+ "loss": 0.608,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.082423243354626,
34
+ "grad_norm": 6.108644485473633,
35
+ "learning_rate": 1.3324175824175824e-05,
36
+ "loss": 0.6063,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.10302905419328251,
41
+ "grad_norm": 3.141345739364624,
42
+ "learning_rate": 1.6758241758241757e-05,
43
+ "loss": 0.5388,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.123634865031939,
48
+ "grad_norm": 4.041093349456787,
49
+ "learning_rate": 2.0192307692307694e-05,
50
+ "loss": 0.4164,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.1442406758705955,
55
+ "grad_norm": 5.099579334259033,
56
+ "learning_rate": 2.348901098901099e-05,
57
+ "loss": 0.3599,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.164846486709252,
62
+ "grad_norm": 2.3562018871307373,
63
+ "learning_rate": 2.6785714285714288e-05,
64
+ "loss": 0.3026,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.1854522975479085,
69
+ "grad_norm": 1.3748841285705566,
70
+ "learning_rate": 3.021978021978022e-05,
71
+ "loss": 0.1953,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.20605810838656502,
76
+ "grad_norm": 5.422688961029053,
77
+ "learning_rate": 3.365384615384616e-05,
78
+ "loss": 0.2107,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.2266639192252215,
83
+ "grad_norm": 3.1931090354919434,
84
+ "learning_rate": 3.708791208791209e-05,
85
+ "loss": 0.1905,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.247269730063878,
90
+ "grad_norm": 7.671177387237549,
91
+ "learning_rate": 4.052197802197803e-05,
92
+ "loss": 0.1454,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.2678755409025345,
97
+ "grad_norm": 5.701260089874268,
98
+ "learning_rate": 4.3956043956043955e-05,
99
+ "loss": 0.1193,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.288481351741191,
104
+ "grad_norm": 4.128372669219971,
105
+ "learning_rate": 4.739010989010989e-05,
106
+ "loss": 0.1242,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.30908716257984753,
111
+ "grad_norm": 2.761212110519409,
112
+ "learning_rate": 4.990839694656489e-05,
113
+ "loss": 0.137,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.329692973418504,
118
+ "grad_norm": 5.561426162719727,
119
+ "learning_rate": 4.952671755725191e-05,
120
+ "loss": 0.1326,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.35029878425716054,
125
+ "grad_norm": 0.6887926459312439,
126
+ "learning_rate": 4.9145038167938934e-05,
127
+ "loss": 0.1149,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.370904595095817,
132
+ "grad_norm": 3.1560258865356445,
133
+ "learning_rate": 4.8763358778625956e-05,
134
+ "loss": 0.1091,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.3915104059344735,
139
+ "grad_norm": 3.2499308586120605,
140
+ "learning_rate": 4.838167938931298e-05,
141
+ "loss": 0.1192,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.41211621677313004,
146
+ "grad_norm": 1.6396406888961792,
147
+ "learning_rate": 4.8e-05,
148
+ "loss": 0.098,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.4327220276117865,
153
+ "grad_norm": 1.4734318256378174,
154
+ "learning_rate": 4.7618320610687024e-05,
155
+ "loss": 0.1064,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.453327838450443,
160
+ "grad_norm": 2.2481157779693604,
161
+ "learning_rate": 4.723664122137405e-05,
162
+ "loss": 0.1099,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.47393364928909953,
167
+ "grad_norm": 2.839649200439453,
168
+ "learning_rate": 4.6854961832061075e-05,
169
+ "loss": 0.0999,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.494539460127756,
174
+ "grad_norm": 0.30553099513053894,
175
+ "learning_rate": 4.64732824427481e-05,
176
+ "loss": 0.0992,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.5151452709664125,
181
+ "grad_norm": 0.589301347732544,
182
+ "learning_rate": 4.609160305343512e-05,
183
+ "loss": 0.0735,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.535751081805069,
188
+ "grad_norm": 2.1147384643554688,
189
+ "learning_rate": 4.570992366412214e-05,
190
+ "loss": 0.0901,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.5563568926437256,
195
+ "grad_norm": 0.805992841720581,
196
+ "learning_rate": 4.5328244274809165e-05,
197
+ "loss": 0.0747,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.576962703482382,
202
+ "grad_norm": 1.168734073638916,
203
+ "learning_rate": 4.494656488549619e-05,
204
+ "loss": 0.067,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 0.5975685143210385,
209
+ "grad_norm": 5.0603790283203125,
210
+ "learning_rate": 4.45648854961832e-05,
211
+ "loss": 0.0677,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 0.6181743251596951,
216
+ "grad_norm": 5.00893497467041,
217
+ "learning_rate": 4.4183206106870225e-05,
218
+ "loss": 0.0538,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 0.6387801359983515,
223
+ "grad_norm": 0.6863914132118225,
224
+ "learning_rate": 4.3801526717557255e-05,
225
+ "loss": 0.0596,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 0.659385946837008,
230
+ "grad_norm": 3.027167797088623,
231
+ "learning_rate": 4.341984732824428e-05,
232
+ "loss": 0.0476,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 0.6799917576756646,
237
+ "grad_norm": 3.794942617416382,
238
+ "learning_rate": 4.30381679389313e-05,
239
+ "loss": 0.0922,
240
+ "step": 825
241
+ },
242
+ {
243
+ "epoch": 0.7005975685143211,
244
+ "grad_norm": 1.6739851236343384,
245
+ "learning_rate": 4.265648854961832e-05,
246
+ "loss": 0.0601,
247
+ "step": 850
248
+ },
249
+ {
250
+ "epoch": 0.7212033793529775,
251
+ "grad_norm": 4.5667195320129395,
252
+ "learning_rate": 4.2274809160305344e-05,
253
+ "loss": 0.0606,
254
+ "step": 875
255
+ },
256
+ {
257
+ "epoch": 0.741809190191634,
258
+ "grad_norm": 1.4475433826446533,
259
+ "learning_rate": 4.189312977099237e-05,
260
+ "loss": 0.0488,
261
+ "step": 900
262
+ },
263
+ {
264
+ "epoch": 0.7624150010302906,
265
+ "grad_norm": 3.672123908996582,
266
+ "learning_rate": 4.151145038167939e-05,
267
+ "loss": 0.066,
268
+ "step": 925
269
+ },
270
+ {
271
+ "epoch": 0.783020811868947,
272
+ "grad_norm": 0.7629732489585876,
273
+ "learning_rate": 4.112977099236641e-05,
274
+ "loss": 0.0533,
275
+ "step": 950
276
+ },
277
+ {
278
+ "epoch": 0.8036266227076035,
279
+ "grad_norm": 3.216966390609741,
280
+ "learning_rate": 4.0748091603053434e-05,
281
+ "loss": 0.0524,
282
+ "step": 975
283
+ },
284
+ {
285
+ "epoch": 0.8242324335462601,
286
+ "grad_norm": 1.6424092054367065,
287
+ "learning_rate": 4.036641221374046e-05,
288
+ "loss": 0.0449,
289
+ "step": 1000
290
+ },
291
+ {
292
+ "epoch": 0.8448382443849165,
293
+ "grad_norm": 3.3341548442840576,
294
+ "learning_rate": 3.9984732824427486e-05,
295
+ "loss": 0.0595,
296
+ "step": 1025
297
+ },
298
+ {
299
+ "epoch": 0.865444055223573,
300
+ "grad_norm": 0.1322302669286728,
301
+ "learning_rate": 3.960305343511451e-05,
302
+ "loss": 0.0717,
303
+ "step": 1050
304
+ },
305
+ {
306
+ "epoch": 0.8860498660622296,
307
+ "grad_norm": 5.5867414474487305,
308
+ "learning_rate": 3.922137404580153e-05,
309
+ "loss": 0.0457,
310
+ "step": 1075
311
+ },
312
+ {
313
+ "epoch": 0.906655676900886,
314
+ "grad_norm": 1.4986252784729004,
315
+ "learning_rate": 3.883969465648855e-05,
316
+ "loss": 0.0395,
317
+ "step": 1100
318
+ },
319
+ {
320
+ "epoch": 0.9272614877395425,
321
+ "grad_norm": 0.7124060392379761,
322
+ "learning_rate": 3.8458015267175575e-05,
323
+ "loss": 0.0463,
324
+ "step": 1125
325
+ },
326
+ {
327
+ "epoch": 0.9478672985781991,
328
+ "grad_norm": 1.1682511568069458,
329
+ "learning_rate": 3.80763358778626e-05,
330
+ "loss": 0.0396,
331
+ "step": 1150
332
+ },
333
+ {
334
+ "epoch": 0.9684731094168556,
335
+ "grad_norm": 4.690053939819336,
336
+ "learning_rate": 3.770992366412214e-05,
337
+ "loss": 0.0428,
338
+ "step": 1175
339
+ },
340
+ {
341
+ "epoch": 0.989078920255512,
342
+ "grad_norm": 1.3264271020889282,
343
+ "learning_rate": 3.732824427480916e-05,
344
+ "loss": 0.06,
345
+ "step": 1200
346
+ },
347
+ {
348
+ "epoch": 0.9997939418916134,
349
+ "eval_accuracy": 0.9912411767736617,
350
+ "eval_f1_macro": 0.9877568131380815,
351
+ "eval_f1_micro": 0.9912411767736617,
352
+ "eval_f1_weighted": 0.9911910099696459,
353
+ "eval_loss": 0.03924937546253204,
354
+ "eval_precision_macro": 0.9939377252247231,
355
+ "eval_precision_micro": 0.9912411767736617,
356
+ "eval_precision_weighted": 0.9912837913018231,
357
+ "eval_recall_macro": 0.9818041226442024,
358
+ "eval_recall_micro": 0.9912411767736617,
359
+ "eval_recall_weighted": 0.9912411767736617,
360
+ "eval_runtime": 18.3314,
361
+ "eval_samples_per_second": 1058.782,
362
+ "eval_steps_per_second": 33.112,
363
+ "step": 1213
364
+ },
365
+ {
366
+ "epoch": 1.0096847310941686,
367
+ "grad_norm": 0.46682170033454895,
368
+ "learning_rate": 3.694656488549619e-05,
369
+ "loss": 0.0372,
370
+ "step": 1225
371
+ },
372
+ {
373
+ "epoch": 1.030290541932825,
374
+ "grad_norm": 3.3791985511779785,
375
+ "learning_rate": 3.656488549618321e-05,
376
+ "loss": 0.0439,
377
+ "step": 1250
378
+ },
379
+ {
380
+ "epoch": 1.0508963527714816,
381
+ "grad_norm": 3.6968090534210205,
382
+ "learning_rate": 3.6183206106870234e-05,
383
+ "loss": 0.0382,
384
+ "step": 1275
385
+ },
386
+ {
387
+ "epoch": 1.071502163610138,
388
+ "grad_norm": 2.349797487258911,
389
+ "learning_rate": 3.580152671755726e-05,
390
+ "loss": 0.0327,
391
+ "step": 1300
392
+ },
393
+ {
394
+ "epoch": 1.0921079744487945,
395
+ "grad_norm": 1.1067183017730713,
396
+ "learning_rate": 3.54351145038168e-05,
397
+ "loss": 0.0315,
398
+ "step": 1325
399
+ },
400
+ {
401
+ "epoch": 1.1127137852874511,
402
+ "grad_norm": 0.032840073108673096,
403
+ "learning_rate": 3.505343511450382e-05,
404
+ "loss": 0.0316,
405
+ "step": 1350
406
+ },
407
+ {
408
+ "epoch": 1.1333195961261076,
409
+ "grad_norm": 0.028824035078287125,
410
+ "learning_rate": 3.467175572519084e-05,
411
+ "loss": 0.0213,
412
+ "step": 1375
413
+ },
414
+ {
415
+ "epoch": 1.153925406964764,
416
+ "grad_norm": 0.5763944983482361,
417
+ "learning_rate": 3.4290076335877864e-05,
418
+ "loss": 0.026,
419
+ "step": 1400
420
+ },
421
+ {
422
+ "epoch": 1.1745312178034206,
423
+ "grad_norm": 0.08884817361831665,
424
+ "learning_rate": 3.3908396946564886e-05,
425
+ "loss": 0.025,
426
+ "step": 1425
427
+ },
428
+ {
429
+ "epoch": 1.195137028642077,
430
+ "grad_norm": 0.41536378860473633,
431
+ "learning_rate": 3.352671755725191e-05,
432
+ "loss": 0.0346,
433
+ "step": 1450
434
+ },
435
+ {
436
+ "epoch": 1.2157428394807335,
437
+ "grad_norm": 0.3112834393978119,
438
+ "learning_rate": 3.314503816793894e-05,
439
+ "loss": 0.0264,
440
+ "step": 1475
441
+ },
442
+ {
443
+ "epoch": 1.2363486503193901,
444
+ "grad_norm": 0.48356932401657104,
445
+ "learning_rate": 3.276335877862596e-05,
446
+ "loss": 0.0188,
447
+ "step": 1500
448
+ },
449
+ {
450
+ "epoch": 1.2569544611580465,
451
+ "grad_norm": 3.8283050060272217,
452
+ "learning_rate": 3.238167938931298e-05,
453
+ "loss": 0.038,
454
+ "step": 1525
455
+ },
456
+ {
457
+ "epoch": 1.2775602719967032,
458
+ "grad_norm": 0.06744606792926788,
459
+ "learning_rate": 3.2000000000000005e-05,
460
+ "loss": 0.0299,
461
+ "step": 1550
462
+ },
463
+ {
464
+ "epoch": 1.2981660828353596,
465
+ "grad_norm": 5.736328125,
466
+ "learning_rate": 3.161832061068703e-05,
467
+ "loss": 0.0243,
468
+ "step": 1575
469
+ },
470
+ {
471
+ "epoch": 1.318771893674016,
472
+ "grad_norm": 0.07336083799600601,
473
+ "learning_rate": 3.123664122137404e-05,
474
+ "loss": 0.0268,
475
+ "step": 1600
476
+ },
477
+ {
478
+ "epoch": 1.3393777045126725,
479
+ "grad_norm": 0.10824728012084961,
480
+ "learning_rate": 3.0854961832061066e-05,
481
+ "loss": 0.0277,
482
+ "step": 1625
483
+ },
484
+ {
485
+ "epoch": 1.359983515351329,
486
+ "grad_norm": 2.3970558643341064,
487
+ "learning_rate": 3.047328244274809e-05,
488
+ "loss": 0.0247,
489
+ "step": 1650
490
+ },
491
+ {
492
+ "epoch": 1.3805893261899855,
493
+ "grad_norm": 0.14330969750881195,
494
+ "learning_rate": 3.0091603053435114e-05,
495
+ "loss": 0.0292,
496
+ "step": 1675
497
+ },
498
+ {
499
+ "epoch": 1.4011951370286422,
500
+ "grad_norm": 0.5449164509773254,
501
+ "learning_rate": 2.970992366412214e-05,
502
+ "loss": 0.026,
503
+ "step": 1700
504
+ },
505
+ {
506
+ "epoch": 1.4218009478672986,
507
+ "grad_norm": 0.13645227253437042,
508
+ "learning_rate": 2.9328244274809162e-05,
509
+ "loss": 0.0337,
510
+ "step": 1725
511
+ },
512
+ {
513
+ "epoch": 1.442406758705955,
514
+ "grad_norm": 0.2142195850610733,
515
+ "learning_rate": 2.8946564885496185e-05,
516
+ "loss": 0.0148,
517
+ "step": 1750
518
+ },
519
+ {
520
+ "epoch": 1.4630125695446115,
521
+ "grad_norm": 0.053218819200992584,
522
+ "learning_rate": 2.8564885496183207e-05,
523
+ "loss": 0.0168,
524
+ "step": 1775
525
+ },
526
+ {
527
+ "epoch": 1.483618380383268,
528
+ "grad_norm": 6.44566011428833,
529
+ "learning_rate": 2.818320610687023e-05,
530
+ "loss": 0.0177,
531
+ "step": 1800
532
+ },
533
+ {
534
+ "epoch": 1.5042241912219247,
535
+ "grad_norm": 0.035187333822250366,
536
+ "learning_rate": 2.7801526717557252e-05,
537
+ "loss": 0.0277,
538
+ "step": 1825
539
+ },
540
+ {
541
+ "epoch": 1.5248300020605812,
542
+ "grad_norm": 0.042209599167108536,
543
+ "learning_rate": 2.7419847328244274e-05,
544
+ "loss": 0.0349,
545
+ "step": 1850
546
+ },
547
+ {
548
+ "epoch": 1.5454358128992376,
549
+ "grad_norm": 4.258108139038086,
550
+ "learning_rate": 2.7038167938931297e-05,
551
+ "loss": 0.0232,
552
+ "step": 1875
553
+ },
554
+ {
555
+ "epoch": 1.566041623737894,
556
+ "grad_norm": 0.2930113673210144,
557
+ "learning_rate": 2.665648854961832e-05,
558
+ "loss": 0.0225,
559
+ "step": 1900
560
+ },
561
+ {
562
+ "epoch": 1.5866474345765504,
563
+ "grad_norm": 4.373762607574463,
564
+ "learning_rate": 2.627480916030535e-05,
565
+ "loss": 0.0216,
566
+ "step": 1925
567
+ },
568
+ {
569
+ "epoch": 1.607253245415207,
570
+ "grad_norm": 1.3070122003555298,
571
+ "learning_rate": 2.589312977099237e-05,
572
+ "loss": 0.0118,
573
+ "step": 1950
574
+ },
575
+ {
576
+ "epoch": 1.6278590562538637,
577
+ "grad_norm": 1.7738819122314453,
578
+ "learning_rate": 2.5511450381679393e-05,
579
+ "loss": 0.024,
580
+ "step": 1975
581
+ },
582
+ {
583
+ "epoch": 1.6484648670925202,
584
+ "grad_norm": 0.027883194386959076,
585
+ "learning_rate": 2.5129770992366412e-05,
586
+ "loss": 0.0186,
587
+ "step": 2000
588
+ },
589
+ {
590
+ "epoch": 1.6690706779311766,
591
+ "grad_norm": 0.030870651826262474,
592
+ "learning_rate": 2.4748091603053435e-05,
593
+ "loss": 0.0174,
594
+ "step": 2025
595
+ },
596
+ {
597
+ "epoch": 1.689676488769833,
598
+ "grad_norm": 0.11152543127536774,
599
+ "learning_rate": 2.4366412213740457e-05,
600
+ "loss": 0.0225,
601
+ "step": 2050
602
+ },
603
+ {
604
+ "epoch": 1.7102822996084894,
605
+ "grad_norm": 0.09863735735416412,
606
+ "learning_rate": 2.3984732824427483e-05,
607
+ "loss": 0.0154,
608
+ "step": 2075
609
+ },
610
+ {
611
+ "epoch": 1.730888110447146,
612
+ "grad_norm": 0.03743008151650429,
613
+ "learning_rate": 2.3603053435114505e-05,
614
+ "loss": 0.0145,
615
+ "step": 2100
616
+ },
617
+ {
618
+ "epoch": 1.7514939212858027,
619
+ "grad_norm": 0.037079595029354095,
620
+ "learning_rate": 2.3221374045801528e-05,
621
+ "loss": 0.0228,
622
+ "step": 2125
623
+ },
624
+ {
625
+ "epoch": 1.7720997321244591,
626
+ "grad_norm": 0.02248048223555088,
627
+ "learning_rate": 2.283969465648855e-05,
628
+ "loss": 0.0302,
629
+ "step": 2150
630
+ },
631
+ {
632
+ "epoch": 1.7927055429631156,
633
+ "grad_norm": 0.5228779911994934,
634
+ "learning_rate": 2.2458015267175573e-05,
635
+ "loss": 0.0304,
636
+ "step": 2175
637
+ },
638
+ {
639
+ "epoch": 1.813311353801772,
640
+ "grad_norm": 0.07086365669965744,
641
+ "learning_rate": 2.20763358778626e-05,
642
+ "loss": 0.0224,
643
+ "step": 2200
644
+ },
645
+ {
646
+ "epoch": 1.8339171646404286,
647
+ "grad_norm": 0.02493666112422943,
648
+ "learning_rate": 2.169465648854962e-05,
649
+ "loss": 0.0135,
650
+ "step": 2225
651
+ },
652
+ {
653
+ "epoch": 1.854522975479085,
654
+ "grad_norm": 1.703371286392212,
655
+ "learning_rate": 2.1312977099236643e-05,
656
+ "loss": 0.0213,
657
+ "step": 2250
658
+ },
659
+ {
660
+ "epoch": 1.8751287863177417,
661
+ "grad_norm": 2.37048602104187,
662
+ "learning_rate": 2.0931297709923666e-05,
663
+ "loss": 0.0245,
664
+ "step": 2275
665
+ },
666
+ {
667
+ "epoch": 1.8957345971563981,
668
+ "grad_norm": 1.9404609203338623,
669
+ "learning_rate": 2.0549618320610688e-05,
670
+ "loss": 0.0249,
671
+ "step": 2300
672
+ },
673
+ {
674
+ "epoch": 1.9163404079950546,
675
+ "grad_norm": 2.3614635467529297,
676
+ "learning_rate": 2.016793893129771e-05,
677
+ "loss": 0.0155,
678
+ "step": 2325
679
+ },
680
+ {
681
+ "epoch": 1.936946218833711,
682
+ "grad_norm": 0.010869844816625118,
683
+ "learning_rate": 1.9786259541984733e-05,
684
+ "loss": 0.011,
685
+ "step": 2350
686
+ },
687
+ {
688
+ "epoch": 1.9575520296723676,
689
+ "grad_norm": 3.8267769813537598,
690
+ "learning_rate": 1.9404580152671755e-05,
691
+ "loss": 0.0194,
692
+ "step": 2375
693
+ },
694
+ {
695
+ "epoch": 1.978157840511024,
696
+ "grad_norm": 1.0191699266433716,
697
+ "learning_rate": 1.902290076335878e-05,
698
+ "loss": 0.024,
699
+ "step": 2400
700
+ },
701
+ {
702
+ "epoch": 1.9987636513496807,
703
+ "grad_norm": 2.944854497909546,
704
+ "learning_rate": 1.8641221374045803e-05,
705
+ "loss": 0.0157,
706
+ "step": 2425
707
+ },
708
+ {
709
+ "epoch": 1.9995878837832268,
710
+ "eval_accuracy": 0.9954144984285641,
711
+ "eval_f1_macro": 0.9934889743246283,
712
+ "eval_f1_micro": 0.9954144984285641,
713
+ "eval_f1_weighted": 0.9954058869538126,
714
+ "eval_loss": 0.02238026075065136,
715
+ "eval_precision_macro": 0.9952598218686433,
716
+ "eval_precision_micro": 0.9954144984285641,
717
+ "eval_precision_weighted": 0.9954125216770092,
718
+ "eval_recall_macro": 0.9917415518445051,
719
+ "eval_recall_micro": 0.9954144984285641,
720
+ "eval_recall_weighted": 0.9954144984285641,
721
+ "eval_runtime": 18.0784,
722
+ "eval_samples_per_second": 1073.599,
723
+ "eval_steps_per_second": 33.576,
724
+ "step": 2426
725
+ },
726
+ {
727
+ "epoch": 2.019369462188337,
728
+ "grad_norm": 0.0203185323625803,
729
+ "learning_rate": 1.8259541984732826e-05,
730
+ "loss": 0.0163,
731
+ "step": 2450
732
+ },
733
+ {
734
+ "epoch": 2.0399752730269936,
735
+ "grad_norm": 0.050282154232263565,
736
+ "learning_rate": 1.787786259541985e-05,
737
+ "loss": 0.023,
738
+ "step": 2475
739
+ },
740
+ {
741
+ "epoch": 2.06058108386565,
742
+ "grad_norm": 1.1421475410461426,
743
+ "learning_rate": 1.749618320610687e-05,
744
+ "loss": 0.0076,
745
+ "step": 2500
746
+ },
747
+ {
748
+ "epoch": 2.0811868947043064,
749
+ "grad_norm": 1.4307163953781128,
750
+ "learning_rate": 1.712977099236641e-05,
751
+ "loss": 0.0237,
752
+ "step": 2525
753
+ },
754
+ {
755
+ "epoch": 2.1017927055429633,
756
+ "grad_norm": 1.7668225765228271,
757
+ "learning_rate": 1.6748091603053437e-05,
758
+ "loss": 0.0097,
759
+ "step": 2550
760
+ },
761
+ {
762
+ "epoch": 2.1223985163816197,
763
+ "grad_norm": 0.43096867203712463,
764
+ "learning_rate": 1.636641221374046e-05,
765
+ "loss": 0.0164,
766
+ "step": 2575
767
+ },
768
+ {
769
+ "epoch": 2.143004327220276,
770
+ "grad_norm": 0.009999148547649384,
771
+ "learning_rate": 1.598473282442748e-05,
772
+ "loss": 0.005,
773
+ "step": 2600
774
+ },
775
+ {
776
+ "epoch": 2.1636101380589325,
777
+ "grad_norm": 0.015757331624627113,
778
+ "learning_rate": 1.5603053435114504e-05,
779
+ "loss": 0.0053,
780
+ "step": 2625
781
+ },
782
+ {
783
+ "epoch": 2.184215948897589,
784
+ "grad_norm": 0.014865142293274403,
785
+ "learning_rate": 1.5221374045801528e-05,
786
+ "loss": 0.0085,
787
+ "step": 2650
788
+ },
789
+ {
790
+ "epoch": 2.2048217597362454,
791
+ "grad_norm": 0.25190040469169617,
792
+ "learning_rate": 1.483969465648855e-05,
793
+ "loss": 0.0108,
794
+ "step": 2675
795
+ },
796
+ {
797
+ "epoch": 2.2254275705749023,
798
+ "grad_norm": 0.048391640186309814,
799
+ "learning_rate": 1.4458015267175573e-05,
800
+ "loss": 0.0015,
801
+ "step": 2700
802
+ },
803
+ {
804
+ "epoch": 2.2460333814135587,
805
+ "grad_norm": 0.03182575851678848,
806
+ "learning_rate": 1.4076335877862595e-05,
807
+ "loss": 0.006,
808
+ "step": 2725
809
+ },
810
+ {
811
+ "epoch": 2.266639192252215,
812
+ "grad_norm": 0.03702850267291069,
813
+ "learning_rate": 1.3694656488549621e-05,
814
+ "loss": 0.0042,
815
+ "step": 2750
816
+ },
817
+ {
818
+ "epoch": 2.2872450030908715,
819
+ "grad_norm": 0.010030820034444332,
820
+ "learning_rate": 1.3312977099236642e-05,
821
+ "loss": 0.0091,
822
+ "step": 2775
823
+ },
824
+ {
825
+ "epoch": 2.307850813929528,
826
+ "grad_norm": 0.42647820711135864,
827
+ "learning_rate": 1.2931297709923664e-05,
828
+ "loss": 0.019,
829
+ "step": 2800
830
+ },
831
+ {
832
+ "epoch": 2.328456624768185,
833
+ "grad_norm": 0.012364137917757034,
834
+ "learning_rate": 1.2549618320610687e-05,
835
+ "loss": 0.0052,
836
+ "step": 2825
837
+ },
838
+ {
839
+ "epoch": 2.3490624356068412,
840
+ "grad_norm": 0.8119286298751831,
841
+ "learning_rate": 1.216793893129771e-05,
842
+ "loss": 0.0058,
843
+ "step": 2850
844
+ },
845
+ {
846
+ "epoch": 2.3696682464454977,
847
+ "grad_norm": 0.03282434120774269,
848
+ "learning_rate": 1.1786259541984733e-05,
849
+ "loss": 0.0114,
850
+ "step": 2875
851
+ },
852
+ {
853
+ "epoch": 2.390274057284154,
854
+ "grad_norm": 0.03597622364759445,
855
+ "learning_rate": 1.1404580152671757e-05,
856
+ "loss": 0.0122,
857
+ "step": 2900
858
+ },
859
+ {
860
+ "epoch": 2.4108798681228105,
861
+ "grad_norm": 0.17078496515750885,
862
+ "learning_rate": 1.1022900763358778e-05,
863
+ "loss": 0.0111,
864
+ "step": 2925
865
+ },
866
+ {
867
+ "epoch": 2.431485678961467,
868
+ "grad_norm": 4.740245342254639,
869
+ "learning_rate": 1.0641221374045802e-05,
870
+ "loss": 0.0082,
871
+ "step": 2950
872
+ },
873
+ {
874
+ "epoch": 2.452091489800124,
875
+ "grad_norm": 0.05649268627166748,
876
+ "learning_rate": 1.0259541984732825e-05,
877
+ "loss": 0.0118,
878
+ "step": 2975
879
+ },
880
+ {
881
+ "epoch": 2.4726973006387802,
882
+ "grad_norm": 0.04967363923788071,
883
+ "learning_rate": 9.877862595419849e-06,
884
+ "loss": 0.0183,
885
+ "step": 3000
886
+ },
887
+ {
888
+ "epoch": 2.4933031114774367,
889
+ "grad_norm": 0.007585471961647272,
890
+ "learning_rate": 9.496183206106871e-06,
891
+ "loss": 0.0044,
892
+ "step": 3025
893
+ },
894
+ {
895
+ "epoch": 2.513908922316093,
896
+ "grad_norm": 0.020672131329774857,
897
+ "learning_rate": 9.114503816793894e-06,
898
+ "loss": 0.0043,
899
+ "step": 3050
900
+ },
901
+ {
902
+ "epoch": 2.5345147331547495,
903
+ "grad_norm": 0.005783187225461006,
904
+ "learning_rate": 8.732824427480916e-06,
905
+ "loss": 0.0049,
906
+ "step": 3075
907
+ },
908
+ {
909
+ "epoch": 2.5551205439934064,
910
+ "grad_norm": 0.0074052768759429455,
911
+ "learning_rate": 8.351145038167938e-06,
912
+ "loss": 0.0016,
913
+ "step": 3100
914
+ },
915
+ {
916
+ "epoch": 2.575726354832063,
917
+ "grad_norm": 0.03194005414843559,
918
+ "learning_rate": 7.969465648854962e-06,
919
+ "loss": 0.0039,
920
+ "step": 3125
921
+ },
922
+ {
923
+ "epoch": 2.5963321656707192,
924
+ "grad_norm": 0.0073048705235123634,
925
+ "learning_rate": 7.587786259541985e-06,
926
+ "loss": 0.0042,
927
+ "step": 3150
928
+ },
929
+ {
930
+ "epoch": 2.6169379765093757,
931
+ "grad_norm": 3.5076446533203125,
932
+ "learning_rate": 7.206106870229008e-06,
933
+ "loss": 0.0052,
934
+ "step": 3175
935
+ },
936
+ {
937
+ "epoch": 2.637543787348032,
938
+ "grad_norm": 0.004831337369978428,
939
+ "learning_rate": 6.8244274809160305e-06,
940
+ "loss": 0.0122,
941
+ "step": 3200
942
+ },
943
+ {
944
+ "epoch": 2.6581495981866885,
945
+ "grad_norm": 0.06588663160800934,
946
+ "learning_rate": 6.442748091603054e-06,
947
+ "loss": 0.0126,
948
+ "step": 3225
949
+ },
950
+ {
951
+ "epoch": 2.678755409025345,
952
+ "grad_norm": 0.11881962418556213,
953
+ "learning_rate": 6.061068702290076e-06,
954
+ "loss": 0.0109,
955
+ "step": 3250
956
+ },
957
+ {
958
+ "epoch": 2.699361219864002,
959
+ "grad_norm": 0.03703455999493599,
960
+ "learning_rate": 5.6793893129770995e-06,
961
+ "loss": 0.0063,
962
+ "step": 3275
963
+ },
964
+ {
965
+ "epoch": 2.719967030702658,
966
+ "grad_norm": 0.015223699621856213,
967
+ "learning_rate": 5.297709923664122e-06,
968
+ "loss": 0.0059,
969
+ "step": 3300
970
+ },
971
+ {
972
+ "epoch": 2.7405728415413146,
973
+ "grad_norm": 2.5166127681732178,
974
+ "learning_rate": 4.916030534351145e-06,
975
+ "loss": 0.0084,
976
+ "step": 3325
977
+ },
978
+ {
979
+ "epoch": 2.761178652379971,
980
+ "grad_norm": 0.007914497517049313,
981
+ "learning_rate": 4.5343511450381684e-06,
982
+ "loss": 0.0038,
983
+ "step": 3350
984
+ },
985
+ {
986
+ "epoch": 2.7817844632186275,
987
+ "grad_norm": 0.015695059671998024,
988
+ "learning_rate": 4.152671755725191e-06,
989
+ "loss": 0.012,
990
+ "step": 3375
991
+ },
992
+ {
993
+ "epoch": 2.8023902740572844,
994
+ "grad_norm": 0.012181021273136139,
995
+ "learning_rate": 3.770992366412214e-06,
996
+ "loss": 0.0205,
997
+ "step": 3400
998
+ },
999
+ {
1000
+ "epoch": 2.822996084895941,
1001
+ "grad_norm": 2.1182310581207275,
1002
+ "learning_rate": 3.389312977099237e-06,
1003
+ "loss": 0.0109,
1004
+ "step": 3425
1005
+ },
1006
+ {
1007
+ "epoch": 2.843601895734597,
1008
+ "grad_norm": 0.04122795909643173,
1009
+ "learning_rate": 3.0076335877862594e-06,
1010
+ "loss": 0.0112,
1011
+ "step": 3450
1012
+ },
1013
+ {
1014
+ "epoch": 2.8642077065732536,
1015
+ "grad_norm": 0.8893581032752991,
1016
+ "learning_rate": 2.6259541984732826e-06,
1017
+ "loss": 0.0062,
1018
+ "step": 3475
1019
+ },
1020
+ {
1021
+ "epoch": 2.88481351741191,
1022
+ "grad_norm": 11.825778007507324,
1023
+ "learning_rate": 2.2442748091603055e-06,
1024
+ "loss": 0.0104,
1025
+ "step": 3500
1026
+ },
1027
+ {
1028
+ "epoch": 2.9054193282505665,
1029
+ "grad_norm": 0.019555876031517982,
1030
+ "learning_rate": 1.8625954198473283e-06,
1031
+ "loss": 0.0095,
1032
+ "step": 3525
1033
+ },
1034
+ {
1035
+ "epoch": 2.926025139089223,
1036
+ "grad_norm": 0.054326750338077545,
1037
+ "learning_rate": 1.4809160305343512e-06,
1038
+ "loss": 0.0117,
1039
+ "step": 3550
1040
+ },
1041
+ {
1042
+ "epoch": 2.9466309499278798,
1043
+ "grad_norm": 0.01002267561852932,
1044
+ "learning_rate": 1.099236641221374e-06,
1045
+ "loss": 0.011,
1046
+ "step": 3575
1047
+ },
1048
+ {
1049
+ "epoch": 2.967236760766536,
1050
+ "grad_norm": 0.13304032385349274,
1051
+ "learning_rate": 7.175572519083969e-07,
1052
+ "loss": 0.0057,
1053
+ "step": 3600
1054
+ },
1055
+ {
1056
+ "epoch": 2.9878425716051926,
1057
+ "grad_norm": 0.027920976281166077,
1058
+ "learning_rate": 3.3587786259541984e-07,
1059
+ "loss": 0.0033,
1060
+ "step": 3625
1061
+ },
1062
+ {
1063
+ "epoch": 2.99938182567484,
1064
+ "eval_accuracy": 0.9955175434076975,
1065
+ "eval_f1_macro": 0.9936121048770471,
1066
+ "eval_f1_micro": 0.9955175434076975,
1067
+ "eval_f1_weighted": 0.9955108152465474,
1068
+ "eval_loss": 0.021347366273403168,
1069
+ "eval_precision_macro": 0.9946094746601329,
1070
+ "eval_precision_micro": 0.9955175434076975,
1071
+ "eval_precision_weighted": 0.9955142956474508,
1072
+ "eval_recall_macro": 0.9926308276207328,
1073
+ "eval_recall_micro": 0.9955175434076975,
1074
+ "eval_recall_weighted": 0.9955175434076975,
1075
+ "eval_runtime": 18.1429,
1076
+ "eval_samples_per_second": 1069.787,
1077
+ "eval_steps_per_second": 33.457,
1078
+ "step": 3639
1079
+ }
1080
+ ],
1081
+ "logging_steps": 25,
1082
+ "max_steps": 3639,
1083
+ "num_input_tokens_seen": 0,
1084
+ "num_train_epochs": 3,
1085
+ "save_steps": 500,
1086
+ "stateful_callbacks": {
1087
+ "EarlyStoppingCallback": {
1088
+ "args": {
1089
+ "early_stopping_patience": 5,
1090
+ "early_stopping_threshold": 0.01
1091
+ },
1092
+ "attributes": {
1093
+ "early_stopping_patience_counter": 1
1094
+ }
1095
+ },
1096
+ "TrainerControl": {
1097
+ "args": {
1098
+ "should_epoch_stop": false,
1099
+ "should_evaluate": false,
1100
+ "should_log": false,
1101
+ "should_save": true,
1102
+ "should_training_stop": true
1103
+ },
1104
+ "attributes": {}
1105
+ }
1106
+ },
1107
+ "total_flos": 1.5317936953288704e+16,
1108
+ "train_batch_size": 16,
1109
+ "trial_name": null,
1110
+ "trial_params": null
1111
+ }
checkpoint-3639/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b53ee85799227f7206b7302cc195ad7607b88637d11506683587c2d8f46661d
3
+ size 5240
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "finiteautomata/bertweet-base-sentiment-analysis",
3
+ "_num_labels": 3,
4
+ "architectures": [
5
+ "RobertaForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "NEG",
17
+ "1": "NEU",
18
+ "2": "POS"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "NEG": 0,
24
+ "NEU": 1,
25
+ "POS": 2
26
+ },
27
+ "layer_norm_eps": 1e-05,
28
+ "max_position_embeddings": 130,
29
+ "model_type": "roberta",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "tokenizer_class": "BertweetTokenizer",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.45.0",
38
+ "type_vocab_size": 1,
39
+ "use_cache": true,
40
+ "vocab_size": 64001
41
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec1a41015d1cbf6fb1eb310fdb119815bb0a7d46ffdb320e51a506efdced8254
3
+ size 539633244
runs/Oct22_17-11-50_r-alohia-autotrain-advanced-5iqztfhh-24d2f-9qr9x/events.out.tfevents.1729617112.r-alohia-autotrain-advanced-5iqztfhh-24d2f-9qr9x.173.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b291327da47dd1ee855641ed978c029f3ccfd29c7a4d538497bef140326afb41
3
- size 27657
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3963ea47b02e5670f0d8dd1df3bc7e9d3584eaf267de6837d8a2b13e29a3391
3
+ size 38761
runs/Oct22_17-11-50_r-alohia-autotrain-advanced-5iqztfhh-24d2f-9qr9x/events.out.tfevents.1729618026.r-alohia-autotrain-advanced-5iqztfhh-24d2f-9qr9x.173.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0f0d02e06a652c718b02e790d89311febfa6bf1a68ea29866ed723029f4c06e
3
+ size 921
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "64000": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 128,
50
+ "normalization": false,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "BertweetTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b53ee85799227f7206b7302cc195ad7607b88637d11506683587c2d8f46661d
3
+ size 5240
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-78oj2-jlrbv/autotrain-data",
3
+ "model": "finiteautomata/bertweet-base-sentiment-analysis",
4
+ "lr": 5e-05,
5
+ "epochs": 3,
6
+ "max_seq_length": 128,
7
+ "batch_size": 16,
8
+ "warmup_ratio": 0.1,
9
+ "gradient_accumulation": 4,
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-78oj2-jlrbv",
21
+ "auto_find_batch_size": false,
22
+ "mixed_precision": "fp16",
23
+ "save_total_limit": 1,
24
+ "push_to_hub": true,
25
+ "eval_strategy": "epoch",
26
+ "username": "alohia",
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