vic35get commited on
Commit
9536da3
·
verified ·
1 Parent(s): c9ec1d7

Upload folder using huggingface_hub

Browse files
checkpoint-3000/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 3,
8
+ "classifier_activation": "silu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 3,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 1,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "id2label": {
24
+ "0": "LABEL_0",
25
+ "1": "LABEL_1",
26
+ "2": "LABEL_2"
27
+ },
28
+ "initializer_cutoff_factor": 2.0,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 1152,
31
+ "label2id": {
32
+ "LABEL_0": 0,
33
+ "LABEL_1": 1,
34
+ "LABEL_2": 2
35
+ },
36
+ "layer_norm_eps": 1e-05,
37
+ "local_attention": 128,
38
+ "local_rope_theta": 10000.0,
39
+ "max_position_embeddings": 8192,
40
+ "mlp_bias": false,
41
+ "mlp_dropout": 0.0,
42
+ "model_type": "modernbert",
43
+ "norm_bias": false,
44
+ "norm_eps": 1e-05,
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 22,
47
+ "pad_token_id": 5,
48
+ "position_embedding_type": "absolute",
49
+ "problem_type": "single_label_classification",
50
+ "repad_logits_with_grad": false,
51
+ "sep_token_id": 4,
52
+ "sparse_pred_ignore_index": -100,
53
+ "sparse_prediction": false,
54
+ "transformers_version": "4.57.3",
55
+ "vocab_size": 50280
56
+ }
checkpoint-3000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1e9dd8c7a6bd41b49d36b4b64ccfd750baca38ab97eefb930e45ac168916cb
3
+ size 598172524
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139c0935905c512bd7b58f3b74ba5f1fa80806cb02ab1e9d6af6072cbf45dea9
3
+ size 1196435275
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
3
+ size 14645
checkpoint-3000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f14135d530866317c60330b4be9687e48d7891f05bdcec7204609fc49e8400ba
3
+ size 1383
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ece0110fb0b2d25f37c2260e42cbd30f7d3840310cef279e68faec3f55fbf643
3
+ size 1465
checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 3000,
3
+ "best_metric": 0.948647254325394,
4
+ "best_model_checkpoint": "trained_model/checkpoint-3000",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.06666666666666667,
14
+ "grad_norm": 19.61471939086914,
15
+ "learning_rate": 4.4e-06,
16
+ "loss": 1.0113,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.13333333333333333,
21
+ "grad_norm": 14.471400260925293,
22
+ "learning_rate": 8.844444444444445e-06,
23
+ "loss": 0.7156,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.2,
28
+ "grad_norm": 47.6197624206543,
29
+ "learning_rate": 1.3288888888888889e-05,
30
+ "loss": 0.5463,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.26666666666666666,
35
+ "grad_norm": 26.47246551513672,
36
+ "learning_rate": 1.7733333333333335e-05,
37
+ "loss": 0.4756,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.3333333333333333,
42
+ "grad_norm": 13.949202537536621,
43
+ "learning_rate": 1.9758024691358028e-05,
44
+ "loss": 0.4115,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.4,
49
+ "grad_norm": 9.107935905456543,
50
+ "learning_rate": 1.92641975308642e-05,
51
+ "loss": 0.3445,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.4666666666666667,
56
+ "grad_norm": NaN,
57
+ "learning_rate": 1.877037037037037e-05,
58
+ "loss": 0.3166,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.5333333333333333,
63
+ "grad_norm": 6.813497066497803,
64
+ "learning_rate": 1.8276543209876544e-05,
65
+ "loss": 0.2688,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.6,
70
+ "grad_norm": 8.58810806274414,
71
+ "learning_rate": 1.7782716049382718e-05,
72
+ "loss": 0.2409,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.6666666666666666,
77
+ "grad_norm": 7.52830171585083,
78
+ "learning_rate": 1.728888888888889e-05,
79
+ "loss": 0.2303,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.7333333333333333,
84
+ "grad_norm": 3.5060839653015137,
85
+ "learning_rate": 1.6795061728395064e-05,
86
+ "loss": 0.2038,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.8,
91
+ "grad_norm": 5.840308666229248,
92
+ "learning_rate": 1.6301234567901238e-05,
93
+ "loss": 0.2039,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.8666666666666667,
98
+ "grad_norm": 4.7977375984191895,
99
+ "learning_rate": 1.5807407407407408e-05,
100
+ "loss": 0.1921,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.9333333333333333,
105
+ "grad_norm": 2.442521572113037,
106
+ "learning_rate": 1.531358024691358e-05,
107
+ "loss": 0.2018,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 1.0,
112
+ "grad_norm": 7.735184669494629,
113
+ "learning_rate": 1.4819753086419754e-05,
114
+ "loss": 0.1802,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 1.0,
119
+ "eval_accuracy": 0.9375833333333333,
120
+ "eval_f1": 0.9374679633171131,
121
+ "eval_loss": 0.17155718803405762,
122
+ "eval_runtime": 135.0249,
123
+ "eval_samples_per_second": 88.873,
124
+ "eval_steps_per_second": 2.777,
125
+ "step": 1500
126
+ },
127
+ {
128
+ "epoch": 1.0666666666666667,
129
+ "grad_norm": 3.5383481979370117,
130
+ "learning_rate": 1.4325925925925928e-05,
131
+ "loss": 0.158,
132
+ "step": 1600
133
+ },
134
+ {
135
+ "epoch": 1.1333333333333333,
136
+ "grad_norm": 5.8269147872924805,
137
+ "learning_rate": 1.3832098765432101e-05,
138
+ "loss": 0.1651,
139
+ "step": 1700
140
+ },
141
+ {
142
+ "epoch": 1.2,
143
+ "grad_norm": 5.028476238250732,
144
+ "learning_rate": 1.3338271604938273e-05,
145
+ "loss": 0.1686,
146
+ "step": 1800
147
+ },
148
+ {
149
+ "epoch": 1.2666666666666666,
150
+ "grad_norm": 9.353516578674316,
151
+ "learning_rate": 1.2844444444444446e-05,
152
+ "loss": 0.1674,
153
+ "step": 1900
154
+ },
155
+ {
156
+ "epoch": 1.3333333333333333,
157
+ "grad_norm": 11.023250579833984,
158
+ "learning_rate": 1.235061728395062e-05,
159
+ "loss": 0.1749,
160
+ "step": 2000
161
+ },
162
+ {
163
+ "epoch": 1.4,
164
+ "grad_norm": 3.2048285007476807,
165
+ "learning_rate": 1.1856790123456791e-05,
166
+ "loss": 0.1618,
167
+ "step": 2100
168
+ },
169
+ {
170
+ "epoch": 1.4666666666666668,
171
+ "grad_norm": 2.9679791927337646,
172
+ "learning_rate": 1.1362962962962964e-05,
173
+ "loss": 0.1786,
174
+ "step": 2200
175
+ },
176
+ {
177
+ "epoch": 1.5333333333333332,
178
+ "grad_norm": 14.835536003112793,
179
+ "learning_rate": 1.0869135802469138e-05,
180
+ "loss": 0.1451,
181
+ "step": 2300
182
+ },
183
+ {
184
+ "epoch": 1.6,
185
+ "grad_norm": 5.776974678039551,
186
+ "learning_rate": 1.0375308641975311e-05,
187
+ "loss": 0.164,
188
+ "step": 2400
189
+ },
190
+ {
191
+ "epoch": 1.6666666666666665,
192
+ "grad_norm": 12.903321266174316,
193
+ "learning_rate": 9.881481481481483e-06,
194
+ "loss": 0.1447,
195
+ "step": 2500
196
+ },
197
+ {
198
+ "epoch": 1.7333333333333334,
199
+ "grad_norm": 8.211164474487305,
200
+ "learning_rate": 9.387654320987654e-06,
201
+ "loss": 0.1691,
202
+ "step": 2600
203
+ },
204
+ {
205
+ "epoch": 1.8,
206
+ "grad_norm": 3.288093090057373,
207
+ "learning_rate": 8.893827160493828e-06,
208
+ "loss": 0.1629,
209
+ "step": 2700
210
+ },
211
+ {
212
+ "epoch": 1.8666666666666667,
213
+ "grad_norm": 7.652830600738525,
214
+ "learning_rate": 8.400000000000001e-06,
215
+ "loss": 0.1489,
216
+ "step": 2800
217
+ },
218
+ {
219
+ "epoch": 1.9333333333333333,
220
+ "grad_norm": 12.427044868469238,
221
+ "learning_rate": 7.906172839506173e-06,
222
+ "loss": 0.1508,
223
+ "step": 2900
224
+ },
225
+ {
226
+ "epoch": 2.0,
227
+ "grad_norm": 19.034095764160156,
228
+ "learning_rate": 7.412345679012346e-06,
229
+ "loss": 0.1689,
230
+ "step": 3000
231
+ },
232
+ {
233
+ "epoch": 2.0,
234
+ "eval_accuracy": 0.94875,
235
+ "eval_f1": 0.948647254325394,
236
+ "eval_loss": 0.15678440034389496,
237
+ "eval_runtime": 134.9499,
238
+ "eval_samples_per_second": 88.922,
239
+ "eval_steps_per_second": 2.779,
240
+ "step": 3000
241
+ }
242
+ ],
243
+ "logging_steps": 100,
244
+ "max_steps": 4500,
245
+ "num_input_tokens_seen": 0,
246
+ "num_train_epochs": 3,
247
+ "save_steps": 500,
248
+ "stateful_callbacks": {
249
+ "TrainerControl": {
250
+ "args": {
251
+ "should_epoch_stop": false,
252
+ "should_evaluate": false,
253
+ "should_log": false,
254
+ "should_save": true,
255
+ "should_training_stop": false
256
+ },
257
+ "attributes": {}
258
+ }
259
+ },
260
+ "total_flos": 1.30851920019456e+17,
261
+ "train_batch_size": 32,
262
+ "trial_name": null,
263
+ "trial_params": null
264
+ }
checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d0c87f85de88294dbeb4e0f938bac5051eac24f795245419c6609bc625bad6f
3
+ size 5777
checkpoint-4500/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 3,
8
+ "classifier_activation": "silu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 3,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 1,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "id2label": {
24
+ "0": "LABEL_0",
25
+ "1": "LABEL_1",
26
+ "2": "LABEL_2"
27
+ },
28
+ "initializer_cutoff_factor": 2.0,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 1152,
31
+ "label2id": {
32
+ "LABEL_0": 0,
33
+ "LABEL_1": 1,
34
+ "LABEL_2": 2
35
+ },
36
+ "layer_norm_eps": 1e-05,
37
+ "local_attention": 128,
38
+ "local_rope_theta": 10000.0,
39
+ "max_position_embeddings": 8192,
40
+ "mlp_bias": false,
41
+ "mlp_dropout": 0.0,
42
+ "model_type": "modernbert",
43
+ "norm_bias": false,
44
+ "norm_eps": 1e-05,
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 22,
47
+ "pad_token_id": 5,
48
+ "position_embedding_type": "absolute",
49
+ "problem_type": "single_label_classification",
50
+ "repad_logits_with_grad": false,
51
+ "sep_token_id": 4,
52
+ "sparse_pred_ignore_index": -100,
53
+ "sparse_prediction": false,
54
+ "transformers_version": "4.57.3",
55
+ "vocab_size": 50280
56
+ }
checkpoint-4500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17b70914ef16a666c7e97ebd813c455efb08839aa1ab3558ff6f3f1075a9041
3
+ size 598172524
checkpoint-4500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:759c4ba783a2dc83d3da677b8c00e067bafc0244e1ebdbde47d11492586f5dd1
3
+ size 1196435275
checkpoint-4500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f9a0f7843a37be87edd23f4e88aa93b38b95cc2c07503eeb1cf2e4632453a2
3
+ size 14645
checkpoint-4500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d0ce0648ec881b3e806302dcdab881643cb6d4e3c51edd6f43c83016deaa284
3
+ size 1383
checkpoint-4500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c1589b63adf8442130f0ececfddee3205e9729c391c1af5594f2f1268c70bf
3
+ size 1465
checkpoint-4500/trainer_state.json ADDED
@@ -0,0 +1,379 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 4500,
3
+ "best_metric": 0.9584511938733902,
4
+ "best_model_checkpoint": "trained_model/checkpoint-4500",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 4500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.06666666666666667,
14
+ "grad_norm": 19.61471939086914,
15
+ "learning_rate": 4.4e-06,
16
+ "loss": 1.0113,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.13333333333333333,
21
+ "grad_norm": 14.471400260925293,
22
+ "learning_rate": 8.844444444444445e-06,
23
+ "loss": 0.7156,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.2,
28
+ "grad_norm": 47.6197624206543,
29
+ "learning_rate": 1.3288888888888889e-05,
30
+ "loss": 0.5463,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.26666666666666666,
35
+ "grad_norm": 26.47246551513672,
36
+ "learning_rate": 1.7733333333333335e-05,
37
+ "loss": 0.4756,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.3333333333333333,
42
+ "grad_norm": 13.949202537536621,
43
+ "learning_rate": 1.9758024691358028e-05,
44
+ "loss": 0.4115,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.4,
49
+ "grad_norm": 9.107935905456543,
50
+ "learning_rate": 1.92641975308642e-05,
51
+ "loss": 0.3445,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.4666666666666667,
56
+ "grad_norm": NaN,
57
+ "learning_rate": 1.877037037037037e-05,
58
+ "loss": 0.3166,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.5333333333333333,
63
+ "grad_norm": 6.813497066497803,
64
+ "learning_rate": 1.8276543209876544e-05,
65
+ "loss": 0.2688,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.6,
70
+ "grad_norm": 8.58810806274414,
71
+ "learning_rate": 1.7782716049382718e-05,
72
+ "loss": 0.2409,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.6666666666666666,
77
+ "grad_norm": 7.52830171585083,
78
+ "learning_rate": 1.728888888888889e-05,
79
+ "loss": 0.2303,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.7333333333333333,
84
+ "grad_norm": 3.5060839653015137,
85
+ "learning_rate": 1.6795061728395064e-05,
86
+ "loss": 0.2038,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.8,
91
+ "grad_norm": 5.840308666229248,
92
+ "learning_rate": 1.6301234567901238e-05,
93
+ "loss": 0.2039,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.8666666666666667,
98
+ "grad_norm": 4.7977375984191895,
99
+ "learning_rate": 1.5807407407407408e-05,
100
+ "loss": 0.1921,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.9333333333333333,
105
+ "grad_norm": 2.442521572113037,
106
+ "learning_rate": 1.531358024691358e-05,
107
+ "loss": 0.2018,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 1.0,
112
+ "grad_norm": 7.735184669494629,
113
+ "learning_rate": 1.4819753086419754e-05,
114
+ "loss": 0.1802,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 1.0,
119
+ "eval_accuracy": 0.9375833333333333,
120
+ "eval_f1": 0.9374679633171131,
121
+ "eval_loss": 0.17155718803405762,
122
+ "eval_runtime": 135.0249,
123
+ "eval_samples_per_second": 88.873,
124
+ "eval_steps_per_second": 2.777,
125
+ "step": 1500
126
+ },
127
+ {
128
+ "epoch": 1.0666666666666667,
129
+ "grad_norm": 3.5383481979370117,
130
+ "learning_rate": 1.4325925925925928e-05,
131
+ "loss": 0.158,
132
+ "step": 1600
133
+ },
134
+ {
135
+ "epoch": 1.1333333333333333,
136
+ "grad_norm": 5.8269147872924805,
137
+ "learning_rate": 1.3832098765432101e-05,
138
+ "loss": 0.1651,
139
+ "step": 1700
140
+ },
141
+ {
142
+ "epoch": 1.2,
143
+ "grad_norm": 5.028476238250732,
144
+ "learning_rate": 1.3338271604938273e-05,
145
+ "loss": 0.1686,
146
+ "step": 1800
147
+ },
148
+ {
149
+ "epoch": 1.2666666666666666,
150
+ "grad_norm": 9.353516578674316,
151
+ "learning_rate": 1.2844444444444446e-05,
152
+ "loss": 0.1674,
153
+ "step": 1900
154
+ },
155
+ {
156
+ "epoch": 1.3333333333333333,
157
+ "grad_norm": 11.023250579833984,
158
+ "learning_rate": 1.235061728395062e-05,
159
+ "loss": 0.1749,
160
+ "step": 2000
161
+ },
162
+ {
163
+ "epoch": 1.4,
164
+ "grad_norm": 3.2048285007476807,
165
+ "learning_rate": 1.1856790123456791e-05,
166
+ "loss": 0.1618,
167
+ "step": 2100
168
+ },
169
+ {
170
+ "epoch": 1.4666666666666668,
171
+ "grad_norm": 2.9679791927337646,
172
+ "learning_rate": 1.1362962962962964e-05,
173
+ "loss": 0.1786,
174
+ "step": 2200
175
+ },
176
+ {
177
+ "epoch": 1.5333333333333332,
178
+ "grad_norm": 14.835536003112793,
179
+ "learning_rate": 1.0869135802469138e-05,
180
+ "loss": 0.1451,
181
+ "step": 2300
182
+ },
183
+ {
184
+ "epoch": 1.6,
185
+ "grad_norm": 5.776974678039551,
186
+ "learning_rate": 1.0375308641975311e-05,
187
+ "loss": 0.164,
188
+ "step": 2400
189
+ },
190
+ {
191
+ "epoch": 1.6666666666666665,
192
+ "grad_norm": 12.903321266174316,
193
+ "learning_rate": 9.881481481481483e-06,
194
+ "loss": 0.1447,
195
+ "step": 2500
196
+ },
197
+ {
198
+ "epoch": 1.7333333333333334,
199
+ "grad_norm": 8.211164474487305,
200
+ "learning_rate": 9.387654320987654e-06,
201
+ "loss": 0.1691,
202
+ "step": 2600
203
+ },
204
+ {
205
+ "epoch": 1.8,
206
+ "grad_norm": 3.288093090057373,
207
+ "learning_rate": 8.893827160493828e-06,
208
+ "loss": 0.1629,
209
+ "step": 2700
210
+ },
211
+ {
212
+ "epoch": 1.8666666666666667,
213
+ "grad_norm": 7.652830600738525,
214
+ "learning_rate": 8.400000000000001e-06,
215
+ "loss": 0.1489,
216
+ "step": 2800
217
+ },
218
+ {
219
+ "epoch": 1.9333333333333333,
220
+ "grad_norm": 12.427044868469238,
221
+ "learning_rate": 7.906172839506173e-06,
222
+ "loss": 0.1508,
223
+ "step": 2900
224
+ },
225
+ {
226
+ "epoch": 2.0,
227
+ "grad_norm": 19.034095764160156,
228
+ "learning_rate": 7.412345679012346e-06,
229
+ "loss": 0.1689,
230
+ "step": 3000
231
+ },
232
+ {
233
+ "epoch": 2.0,
234
+ "eval_accuracy": 0.94875,
235
+ "eval_f1": 0.948647254325394,
236
+ "eval_loss": 0.15678440034389496,
237
+ "eval_runtime": 134.9499,
238
+ "eval_samples_per_second": 88.922,
239
+ "eval_steps_per_second": 2.779,
240
+ "step": 3000
241
+ },
242
+ {
243
+ "epoch": 2.066666666666667,
244
+ "grad_norm": 10.550028800964355,
245
+ "learning_rate": 6.918518518518519e-06,
246
+ "loss": 0.1327,
247
+ "step": 3100
248
+ },
249
+ {
250
+ "epoch": 2.1333333333333333,
251
+ "grad_norm": 8.336569786071777,
252
+ "learning_rate": 6.424691358024692e-06,
253
+ "loss": 0.1332,
254
+ "step": 3200
255
+ },
256
+ {
257
+ "epoch": 2.2,
258
+ "grad_norm": 8.286913871765137,
259
+ "learning_rate": 5.930864197530864e-06,
260
+ "loss": 0.129,
261
+ "step": 3300
262
+ },
263
+ {
264
+ "epoch": 2.2666666666666666,
265
+ "grad_norm": 21.938156127929688,
266
+ "learning_rate": 5.4370370370370376e-06,
267
+ "loss": 0.1267,
268
+ "step": 3400
269
+ },
270
+ {
271
+ "epoch": 2.3333333333333335,
272
+ "grad_norm": 4.7778825759887695,
273
+ "learning_rate": 4.94320987654321e-06,
274
+ "loss": 0.1221,
275
+ "step": 3500
276
+ },
277
+ {
278
+ "epoch": 2.4,
279
+ "grad_norm": 15.925739288330078,
280
+ "learning_rate": 4.449382716049383e-06,
281
+ "loss": 0.1156,
282
+ "step": 3600
283
+ },
284
+ {
285
+ "epoch": 2.466666666666667,
286
+ "grad_norm": 2.2890524864196777,
287
+ "learning_rate": 3.955555555555556e-06,
288
+ "loss": 0.1067,
289
+ "step": 3700
290
+ },
291
+ {
292
+ "epoch": 2.533333333333333,
293
+ "grad_norm": 4.421731948852539,
294
+ "learning_rate": 3.461728395061729e-06,
295
+ "loss": 0.1006,
296
+ "step": 3800
297
+ },
298
+ {
299
+ "epoch": 2.6,
300
+ "grad_norm": 54.37298583984375,
301
+ "learning_rate": 2.9679012345679013e-06,
302
+ "loss": 0.1013,
303
+ "step": 3900
304
+ },
305
+ {
306
+ "epoch": 2.6666666666666665,
307
+ "grad_norm": 13.42692756652832,
308
+ "learning_rate": 2.4740740740740742e-06,
309
+ "loss": 0.1125,
310
+ "step": 4000
311
+ },
312
+ {
313
+ "epoch": 2.7333333333333334,
314
+ "grad_norm": 0.711950957775116,
315
+ "learning_rate": 1.980246913580247e-06,
316
+ "loss": 0.1171,
317
+ "step": 4100
318
+ },
319
+ {
320
+ "epoch": 2.8,
321
+ "grad_norm": 0.9817278385162354,
322
+ "learning_rate": 1.4864197530864199e-06,
323
+ "loss": 0.1105,
324
+ "step": 4200
325
+ },
326
+ {
327
+ "epoch": 2.8666666666666667,
328
+ "grad_norm": 31.010404586791992,
329
+ "learning_rate": 9.925925925925926e-07,
330
+ "loss": 0.1073,
331
+ "step": 4300
332
+ },
333
+ {
334
+ "epoch": 2.9333333333333336,
335
+ "grad_norm": 7.680997848510742,
336
+ "learning_rate": 4.987654320987655e-07,
337
+ "loss": 0.1187,
338
+ "step": 4400
339
+ },
340
+ {
341
+ "epoch": 3.0,
342
+ "grad_norm": 5.868310451507568,
343
+ "learning_rate": 4.938271604938272e-09,
344
+ "loss": 0.1061,
345
+ "step": 4500
346
+ },
347
+ {
348
+ "epoch": 3.0,
349
+ "eval_accuracy": 0.9585833333333333,
350
+ "eval_f1": 0.9584511938733902,
351
+ "eval_loss": 0.1317964494228363,
352
+ "eval_runtime": 135.9928,
353
+ "eval_samples_per_second": 88.24,
354
+ "eval_steps_per_second": 2.757,
355
+ "step": 4500
356
+ }
357
+ ],
358
+ "logging_steps": 100,
359
+ "max_steps": 4500,
360
+ "num_input_tokens_seen": 0,
361
+ "num_train_epochs": 3,
362
+ "save_steps": 500,
363
+ "stateful_callbacks": {
364
+ "TrainerControl": {
365
+ "args": {
366
+ "should_epoch_stop": false,
367
+ "should_evaluate": false,
368
+ "should_log": false,
369
+ "should_save": true,
370
+ "should_training_stop": true
371
+ },
372
+ "attributes": {}
373
+ }
374
+ },
375
+ "total_flos": 1.96277880029184e+17,
376
+ "train_batch_size": 32,
377
+ "trial_name": null,
378
+ "trial_params": null
379
+ }
checkpoint-4500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d0c87f85de88294dbeb4e0f938bac5051eac24f795245419c6609bc625bad6f
3
+ size 5777
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 3,
8
+ "classifier_activation": "silu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 3,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 1,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "id2label": {
24
+ "0": "LABEL_0",
25
+ "1": "LABEL_1",
26
+ "2": "LABEL_2"
27
+ },
28
+ "initializer_cutoff_factor": 2.0,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 1152,
31
+ "label2id": {
32
+ "LABEL_0": 0,
33
+ "LABEL_1": 1,
34
+ "LABEL_2": 2
35
+ },
36
+ "layer_norm_eps": 1e-05,
37
+ "local_attention": 128,
38
+ "local_rope_theta": 10000.0,
39
+ "max_position_embeddings": 8192,
40
+ "mlp_bias": false,
41
+ "mlp_dropout": 0.0,
42
+ "model_type": "modernbert",
43
+ "norm_bias": false,
44
+ "norm_eps": 1e-05,
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 22,
47
+ "pad_token_id": 5,
48
+ "position_embedding_type": "absolute",
49
+ "problem_type": "single_label_classification",
50
+ "repad_logits_with_grad": false,
51
+ "sep_token_id": 4,
52
+ "sparse_pred_ignore_index": -100,
53
+ "sparse_prediction": false,
54
+ "transformers_version": "4.57.3",
55
+ "vocab_size": 50280
56
+ }
label_mapping.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "label_to_id": {
3
+ "edital": 0,
4
+ "licitação": 1,
5
+ "outro": 2
6
+ },
7
+ "id_to_label": {
8
+ "0": "edital",
9
+ "1": "licitação",
10
+ "2": "outro"
11
+ }
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17b70914ef16a666c7e97ebd813c455efb08839aa1ab3558ff6f3f1075a9041
3
+ size 598172524
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|padding|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|endoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[PAD]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "[MASK]",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "clean_up_tokenization_spaces": true,
61
+ "cls_token": "[CLS]",
62
+ "extra_special_tokens": {},
63
+ "mask_token": "[MASK]",
64
+ "model_input_names": [
65
+ "input_ids",
66
+ "attention_mask"
67
+ ],
68
+ "model_max_length": 8192,
69
+ "pad_token": "[PAD]",
70
+ "sep_token": "[SEP]",
71
+ "tokenizer_class": "PreTrainedTokenizerFast",
72
+ "unk_token": "[UNK]"
73
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d0c87f85de88294dbeb4e0f938bac5051eac24f795245419c6609bc625bad6f
3
+ size 5777