Hugging Face's logo

MuhammadHelmy
/
distilbert-base-AuthId

Safetensors
distilbert
Model card Files
xet
Community
MuhammadHelmy commited on
Commit
6c71039
·
verified ·
1 Parent(s): 38b5b0c

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. checkpoint-7500/config.json +71 -0
  2. checkpoint-7500/model.safetensors +3 -0
  3. checkpoint-7500/optimizer.pt +3 -0
  4. checkpoint-7500/rng_state.pth +3 -0
  5. checkpoint-7500/scheduler.pt +3 -0
  6. checkpoint-7500/special_tokens_map.json +37 -0
  7. checkpoint-7500/tokenizer.json +0 -0
  8. checkpoint-7500/tokenizer_config.json +56 -0
  9. checkpoint-7500/trainer_state.json +319 -0
  10. checkpoint-7500/training_args.bin +3 -0
  11. checkpoint-7500/vocab.txt +0 -0
  12. checkpoint-8236/config.json +71 -0
  13. checkpoint-8236/model.safetensors +3 -0
  14. checkpoint-8236/optimizer.pt +3 -0
  15. checkpoint-8236/rng_state.pth +3 -0
  16. checkpoint-8236/scheduler.pt +3 -0
  17. checkpoint-8236/special_tokens_map.json +37 -0
  18. checkpoint-8236/tokenizer.json +0 -0
  19. checkpoint-8236/tokenizer_config.json +56 -0
  20. checkpoint-8236/trainer_state.json +338 -0
  21. checkpoint-8236/training_args.bin +3 -0
  22. checkpoint-8236/vocab.txt +0 -0
checkpoint-7500/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13",
25
+ "14": "LABEL_14",
26
+ "15": "LABEL_15",
27
+ "16": "LABEL_16",
28
+ "17": "LABEL_17",
29
+ "18": "LABEL_18",
30
+ "19": "LABEL_19",
31
+ "20": "LABEL_20"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1,
37
+ "LABEL_10": 10,
38
+ "LABEL_11": 11,
39
+ "LABEL_12": 12,
40
+ "LABEL_13": 13,
41
+ "LABEL_14": 14,
42
+ "LABEL_15": 15,
43
+ "LABEL_16": 16,
44
+ "LABEL_17": 17,
45
+ "LABEL_18": 18,
46
+ "LABEL_19": 19,
47
+ "LABEL_2": 2,
48
+ "LABEL_20": 20,
49
+ "LABEL_3": 3,
50
+ "LABEL_4": 4,
51
+ "LABEL_5": 5,
52
+ "LABEL_6": 6,
53
+ "LABEL_7": 7,
54
+ "LABEL_8": 8,
55
+ "LABEL_9": 9
56
+ },
57
+ "max_position_embeddings": 512,
58
+ "model_type": "distilbert",
59
+ "n_heads": 12,
60
+ "n_layers": 6,
61
+ "output_past": true,
62
+ "pad_token_id": 0,
63
+ "problem_type": "single_label_classification",
64
+ "qa_dropout": 0.1,
65
+ "seq_classif_dropout": 0.2,
66
+ "sinusoidal_pos_embds": false,
67
+ "tie_weights_": true,
68
+ "torch_dtype": "float32",
69
+ "transformers_version": "4.52.4",
70
+ "vocab_size": 119547
71
+ }
checkpoint-7500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b447bfea7bb6819377e4bc9d0017e0ab2ef9ae6ecd0dd40c942d9b10c0f84813
3
+ size 541375820
checkpoint-7500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c339221ce89f64717876c8d8fabb0be656009767716741cdc6be194d5b0f4d4
3
+ size 1082813754
checkpoint-7500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c2f3a5c7fc54692d0487a13705cf9d02e88136c3a95e75ac8c71c9c37468837
3
+ size 14244
checkpoint-7500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c510928b4428c49d3a993c5f72a9e1be30277be840fb66eeb42ec30a0e2ffee
3
+ size 1064
checkpoint-7500/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": false,
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
+ }
checkpoint-7500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-7500/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-7500/trainer_state.json ADDED
@@ -0,0 +1,319 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 7500,
3
+ "best_metric": 0.7842453714436081,
4
+ "best_model_checkpoint": "./distilbert-base-AuthId/checkpoint-7500",
5
+ "epoch": 3.642544924720738,
6
+ "eval_steps": 500,
7
+ "global_step": 7500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.24283632831471588,
14
+ "grad_norm": 10.536812782287598,
15
+ "learning_rate": 4.8446601941747576e-05,
16
+ "loss": 2.4424,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.24283632831471588,
21
+ "eval_accuracy": 0.4645176810199663,
22
+ "eval_f1_macro": 0.38214194553778474,
23
+ "eval_loss": 1.7513902187347412,
24
+ "eval_precision_macro": 0.42410548716505947,
25
+ "eval_recall_macro": 0.4570777134531091,
26
+ "eval_runtime": 44.1019,
27
+ "eval_samples_per_second": 94.259,
28
+ "eval_steps_per_second": 5.895,
29
+ "step": 500
30
+ },
31
+ {
32
+ "epoch": 0.48567265662943176,
33
+ "grad_norm": 8.661422729492188,
34
+ "learning_rate": 7.989001438410175e-05,
35
+ "loss": 1.3721,
36
+ "step": 1000
37
+ },
38
+ {
39
+ "epoch": 0.48567265662943176,
40
+ "eval_accuracy": 0.5208082751984604,
41
+ "eval_f1_macro": 0.4454367070109959,
42
+ "eval_loss": 1.5558406114578247,
43
+ "eval_precision_macro": 0.49026128200564273,
44
+ "eval_recall_macro": 0.5024706104342445,
45
+ "eval_runtime": 44.445,
46
+ "eval_samples_per_second": 93.531,
47
+ "eval_steps_per_second": 5.85,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 0.7285089849441476,
52
+ "grad_norm": 11.807583808898926,
53
+ "learning_rate": 7.837406915300635e-05,
54
+ "loss": 0.9647,
55
+ "step": 1500
56
+ },
57
+ {
58
+ "epoch": 0.7285089849441476,
59
+ "eval_accuracy": 0.6812605244166466,
60
+ "eval_f1_macro": 0.5864448295094548,
61
+ "eval_loss": 1.1119331121444702,
62
+ "eval_precision_macro": 0.5984183492980578,
63
+ "eval_recall_macro": 0.6268369019392432,
64
+ "eval_runtime": 44.5983,
65
+ "eval_samples_per_second": 93.21,
66
+ "eval_steps_per_second": 5.83,
67
+ "step": 1500
68
+ },
69
+ {
70
+ "epoch": 0.9713453132588635,
71
+ "grad_norm": 27.49161720275879,
72
+ "learning_rate": 7.514108265155405e-05,
73
+ "loss": 0.7867,
74
+ "step": 2000
75
+ },
76
+ {
77
+ "epoch": 0.9713453132588635,
78
+ "eval_accuracy": 0.713014192927592,
79
+ "eval_f1_macro": 0.6520857054306285,
80
+ "eval_loss": 1.003157615661621,
81
+ "eval_precision_macro": 0.6618591636767543,
82
+ "eval_recall_macro": 0.6977243147676733,
83
+ "eval_runtime": 45.2348,
84
+ "eval_samples_per_second": 91.898,
85
+ "eval_steps_per_second": 5.748,
86
+ "step": 2000
87
+ },
88
+ {
89
+ "epoch": 1.2141816415735793,
90
+ "grad_norm": 17.49410629272461,
91
+ "learning_rate": 7.033571431701654e-05,
92
+ "loss": 0.5712,
93
+ "step": 2500
94
+ },
95
+ {
96
+ "epoch": 1.2141816415735793,
97
+ "eval_accuracy": 0.7101274957902334,
98
+ "eval_f1_macro": 0.6578185186923463,
99
+ "eval_loss": 1.0687695741653442,
100
+ "eval_precision_macro": 0.6947126776112352,
101
+ "eval_recall_macro": 0.6807690177369954,
102
+ "eval_runtime": 45.4304,
103
+ "eval_samples_per_second": 91.503,
104
+ "eval_steps_per_second": 5.723,
105
+ "step": 2500
106
+ },
107
+ {
108
+ "epoch": 1.4570179698882952,
109
+ "grad_norm": 14.797587394714355,
110
+ "learning_rate": 6.417297954733794e-05,
111
+ "loss": 0.5118,
112
+ "step": 3000
113
+ },
114
+ {
115
+ "epoch": 1.4570179698882952,
116
+ "eval_accuracy": 0.7466923261967765,
117
+ "eval_f1_macro": 0.6802785705299167,
118
+ "eval_loss": 0.9464945197105408,
119
+ "eval_precision_macro": 0.6962547831411214,
120
+ "eval_recall_macro": 0.7067511752266095,
121
+ "eval_runtime": 45.0782,
122
+ "eval_samples_per_second": 92.217,
123
+ "eval_steps_per_second": 5.768,
124
+ "step": 3000
125
+ },
126
+ {
127
+ "epoch": 1.6998542982030111,
128
+ "grad_norm": 11.592080116271973,
129
+ "learning_rate": 5.692862887331573e-05,
130
+ "loss": 0.4238,
131
+ "step": 3500
132
+ },
133
+ {
134
+ "epoch": 1.6998542982030111,
135
+ "eval_accuracy": 0.7529468366610537,
136
+ "eval_f1_macro": 0.6887735293131003,
137
+ "eval_loss": 1.0284276008605957,
138
+ "eval_precision_macro": 0.7004815690389604,
139
+ "eval_recall_macro": 0.7209895448469402,
140
+ "eval_runtime": 45.0958,
141
+ "eval_samples_per_second": 92.182,
142
+ "eval_steps_per_second": 5.766,
143
+ "step": 3500
144
+ },
145
+ {
146
+ "epoch": 1.942690626517727,
147
+ "grad_norm": 1.7279024124145508,
148
+ "learning_rate": 4.892680954747708e-05,
149
+ "loss": 0.383,
150
+ "step": 4000
151
+ },
152
+ {
153
+ "epoch": 1.942690626517727,
154
+ "eval_accuracy": 0.7784459947077219,
155
+ "eval_f1_macro": 0.7004470067611618,
156
+ "eval_loss": 0.9373700618743896,
157
+ "eval_precision_macro": 0.7012745858922871,
158
+ "eval_recall_macro": 0.7363165995805543,
159
+ "eval_runtime": 45.0166,
160
+ "eval_samples_per_second": 92.344,
161
+ "eval_steps_per_second": 5.776,
162
+ "step": 4000
163
+ },
164
+ {
165
+ "epoch": 2.1855269548324427,
166
+ "grad_norm": 11.464333534240723,
167
+ "learning_rate": 4.052556162978074e-05,
168
+ "loss": 0.2498,
169
+ "step": 4500
170
+ },
171
+ {
172
+ "epoch": 2.1855269548324427,
173
+ "eval_accuracy": 0.7897522251623768,
174
+ "eval_f1_macro": 0.736934271206392,
175
+ "eval_loss": 0.8516831398010254,
176
+ "eval_precision_macro": 0.7471052855094972,
177
+ "eval_recall_macro": 0.7513822718605427,
178
+ "eval_runtime": 45.2063,
179
+ "eval_samples_per_second": 91.956,
180
+ "eval_steps_per_second": 5.751,
181
+ "step": 4500
182
+ },
183
+ {
184
+ "epoch": 2.4283632831471587,
185
+ "grad_norm": 13.227448463439941,
186
+ "learning_rate": 3.2100797545350794e-05,
187
+ "loss": 0.2012,
188
+ "step": 5000
189
+ },
190
+ {
191
+ "epoch": 2.4283632831471587,
192
+ "eval_accuracy": 0.7952850613423141,
193
+ "eval_f1_macro": 0.7384644794255656,
194
+ "eval_loss": 0.8422956466674805,
195
+ "eval_precision_macro": 0.7407858112231859,
196
+ "eval_recall_macro": 0.7593629429944239,
197
+ "eval_runtime": 45.0668,
198
+ "eval_samples_per_second": 92.241,
199
+ "eval_steps_per_second": 5.769,
200
+ "step": 5000
201
+ },
202
+ {
203
+ "epoch": 2.6711996114618746,
204
+ "grad_norm": 14.610297203063965,
205
+ "learning_rate": 2.402948194623674e-05,
206
+ "loss": 0.1888,
207
+ "step": 5500
208
+ },
209
+ {
210
+ "epoch": 2.6711996114618746,
211
+ "eval_accuracy": 0.8383449603079144,
212
+ "eval_f1_macro": 0.7668856441209034,
213
+ "eval_loss": 0.7612192034721375,
214
+ "eval_precision_macro": 0.759848794474667,
215
+ "eval_recall_macro": 0.7875978932242379,
216
+ "eval_runtime": 44.9628,
217
+ "eval_samples_per_second": 92.454,
218
+ "eval_steps_per_second": 5.783,
219
+ "step": 5500
220
+ },
221
+ {
222
+ "epoch": 2.9140359397765905,
223
+ "grad_norm": 2.9459526538848877,
224
+ "learning_rate": 1.667276449145691e-05,
225
+ "loss": 0.1478,
226
+ "step": 6000
227
+ },
228
+ {
229
+ "epoch": 2.9140359397765905,
230
+ "eval_accuracy": 0.8284820784219389,
231
+ "eval_f1_macro": 0.7648949869466338,
232
+ "eval_loss": 0.7956407070159912,
233
+ "eval_precision_macro": 0.7582819516660327,
234
+ "eval_recall_macro": 0.7872534623468304,
235
+ "eval_runtime": 45.0026,
236
+ "eval_samples_per_second": 92.372,
237
+ "eval_steps_per_second": 5.777,
238
+ "step": 6000
239
+ },
240
+ {
241
+ "epoch": 3.1568722680913064,
242
+ "grad_norm": 0.04966867342591286,
243
+ "learning_rate": 1.035982026624521e-05,
244
+ "loss": 0.0805,
245
+ "step": 6500
246
+ },
247
+ {
248
+ "epoch": 3.1568722680913064,
249
+ "eval_accuracy": 0.8397883088765937,
250
+ "eval_f1_macro": 0.779163123362359,
251
+ "eval_loss": 0.7845637798309326,
252
+ "eval_precision_macro": 0.7736785485737475,
253
+ "eval_recall_macro": 0.7972932500440235,
254
+ "eval_runtime": 44.623,
255
+ "eval_samples_per_second": 93.158,
256
+ "eval_steps_per_second": 5.827,
257
+ "step": 6500
258
+ },
259
+ {
260
+ "epoch": 3.3997085964060223,
261
+ "grad_norm": 0.054828643798828125,
262
+ "learning_rate": 5.373120898224163e-06,
263
+ "loss": 0.054,
264
+ "step": 7000
265
+ },
266
+ {
267
+ "epoch": 3.3997085964060223,
268
+ "eval_accuracy": 0.8390666345922541,
269
+ "eval_f1_macro": 0.7789886096417518,
270
+ "eval_loss": 0.8231712579727173,
271
+ "eval_precision_macro": 0.7722144919792829,
272
+ "eval_recall_macro": 0.7985903156380745,
273
+ "eval_runtime": 44.6487,
274
+ "eval_samples_per_second": 93.105,
275
+ "eval_steps_per_second": 5.823,
276
+ "step": 7000
277
+ },
278
+ {
279
+ "epoch": 3.642544924720738,
280
+ "grad_norm": 8.141491889953613,
281
+ "learning_rate": 1.935795411934156e-06,
282
+ "loss": 0.0683,
283
+ "step": 7500
284
+ },
285
+ {
286
+ "epoch": 3.642544924720738,
287
+ "eval_accuracy": 0.8448400288669714,
288
+ "eval_f1_macro": 0.7842453714436081,
289
+ "eval_loss": 0.7753947377204895,
290
+ "eval_precision_macro": 0.7754804853445821,
291
+ "eval_recall_macro": 0.8051232260351716,
292
+ "eval_runtime": 45.7414,
293
+ "eval_samples_per_second": 90.881,
294
+ "eval_steps_per_second": 5.684,
295
+ "step": 7500
296
+ }
297
+ ],
298
+ "logging_steps": 500,
299
+ "max_steps": 8236,
300
+ "num_input_tokens_seen": 0,
301
+ "num_train_epochs": 4,
302
+ "save_steps": 500,
303
+ "stateful_callbacks": {
304
+ "TrainerControl": {
305
+ "args": {
306
+ "should_epoch_stop": false,
307
+ "should_evaluate": false,
308
+ "should_log": false,
309
+ "should_save": true,
310
+ "should_training_stop": false
311
+ },
312
+ "attributes": {}
313
+ }
314
+ },
315
+ "total_flos": 1.5900281427207168e+16,
316
+ "train_batch_size": 16,
317
+ "trial_name": null,
318
+ "trial_params": null
319
+ }
checkpoint-7500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c62d5b95ae007f7f68dfb168685d5940013d7e1bd191a6beea90ad5b2a515d2
3
+ size 5304
checkpoint-7500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8236/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13",
25
+ "14": "LABEL_14",
26
+ "15": "LABEL_15",
27
+ "16": "LABEL_16",
28
+ "17": "LABEL_17",
29
+ "18": "LABEL_18",
30
+ "19": "LABEL_19",
31
+ "20": "LABEL_20"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1,
37
+ "LABEL_10": 10,
38
+ "LABEL_11": 11,
39
+ "LABEL_12": 12,
40
+ "LABEL_13": 13,
41
+ "LABEL_14": 14,
42
+ "LABEL_15": 15,
43
+ "LABEL_16": 16,
44
+ "LABEL_17": 17,
45
+ "LABEL_18": 18,
46
+ "LABEL_19": 19,
47
+ "LABEL_2": 2,
48
+ "LABEL_20": 20,
49
+ "LABEL_3": 3,
50
+ "LABEL_4": 4,
51
+ "LABEL_5": 5,
52
+ "LABEL_6": 6,
53
+ "LABEL_7": 7,
54
+ "LABEL_8": 8,
55
+ "LABEL_9": 9
56
+ },
57
+ "max_position_embeddings": 512,
58
+ "model_type": "distilbert",
59
+ "n_heads": 12,
60
+ "n_layers": 6,
61
+ "output_past": true,
62
+ "pad_token_id": 0,
63
+ "problem_type": "single_label_classification",
64
+ "qa_dropout": 0.1,
65
+ "seq_classif_dropout": 0.2,
66
+ "sinusoidal_pos_embds": false,
67
+ "tie_weights_": true,
68
+ "torch_dtype": "float32",
69
+ "transformers_version": "4.52.4",
70
+ "vocab_size": 119547
71
+ }
checkpoint-8236/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8c09c964704450d30bdf16a7bce3bd35bf7cad7584aaf22d0887c8d8c4049d8
3
+ size 541375820
checkpoint-8236/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbd604e8121a1aad18c07afe65fdd51c8847b353dc9b5e7799c19f6796f67a53
3
+ size 1082813754
checkpoint-8236/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f02a331b8c1685303ee1bd826ee3941a0f7b04e224e46dfc2aba6569c30d8d2
3
+ size 14244
checkpoint-8236/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e2b1f25c371d63298550c6da386797b1ba9ea81a1fd6253e3b886b2bcc792d7
3
+ size 1064
checkpoint-8236/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": false,
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
+ }
checkpoint-8236/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8236/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-8236/trainer_state.json ADDED
@@ -0,0 +1,338 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 7500,
3
+ "best_metric": 0.7842453714436081,
4
+ "best_model_checkpoint": "./distilbert-base-AuthId/checkpoint-7500",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 8236,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.24283632831471588,
14
+ "grad_norm": 10.536812782287598,
15
+ "learning_rate": 4.8446601941747576e-05,
16
+ "loss": 2.4424,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.24283632831471588,
21
+ "eval_accuracy": 0.4645176810199663,
22
+ "eval_f1_macro": 0.38214194553778474,
23
+ "eval_loss": 1.7513902187347412,
24
+ "eval_precision_macro": 0.42410548716505947,
25
+ "eval_recall_macro": 0.4570777134531091,
26
+ "eval_runtime": 44.1019,
27
+ "eval_samples_per_second": 94.259,
28
+ "eval_steps_per_second": 5.895,
29
+ "step": 500
30
+ },
31
+ {
32
+ "epoch": 0.48567265662943176,
33
+ "grad_norm": 8.661422729492188,
34
+ "learning_rate": 7.989001438410175e-05,
35
+ "loss": 1.3721,
36
+ "step": 1000
37
+ },
38
+ {
39
+ "epoch": 0.48567265662943176,
40
+ "eval_accuracy": 0.5208082751984604,
41
+ "eval_f1_macro": 0.4454367070109959,
42
+ "eval_loss": 1.5558406114578247,
43
+ "eval_precision_macro": 0.49026128200564273,
44
+ "eval_recall_macro": 0.5024706104342445,
45
+ "eval_runtime": 44.445,
46
+ "eval_samples_per_second": 93.531,
47
+ "eval_steps_per_second": 5.85,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 0.7285089849441476,
52
+ "grad_norm": 11.807583808898926,
53
+ "learning_rate": 7.837406915300635e-05,
54
+ "loss": 0.9647,
55
+ "step": 1500
56
+ },
57
+ {
58
+ "epoch": 0.7285089849441476,
59
+ "eval_accuracy": 0.6812605244166466,
60
+ "eval_f1_macro": 0.5864448295094548,
61
+ "eval_loss": 1.1119331121444702,
62
+ "eval_precision_macro": 0.5984183492980578,
63
+ "eval_recall_macro": 0.6268369019392432,
64
+ "eval_runtime": 44.5983,
65
+ "eval_samples_per_second": 93.21,
66
+ "eval_steps_per_second": 5.83,
67
+ "step": 1500
68
+ },
69
+ {
70
+ "epoch": 0.9713453132588635,
71
+ "grad_norm": 27.49161720275879,
72
+ "learning_rate": 7.514108265155405e-05,
73
+ "loss": 0.7867,
74
+ "step": 2000
75
+ },
76
+ {
77
+ "epoch": 0.9713453132588635,
78
+ "eval_accuracy": 0.713014192927592,
79
+ "eval_f1_macro": 0.6520857054306285,
80
+ "eval_loss": 1.003157615661621,
81
+ "eval_precision_macro": 0.6618591636767543,
82
+ "eval_recall_macro": 0.6977243147676733,
83
+ "eval_runtime": 45.2348,
84
+ "eval_samples_per_second": 91.898,
85
+ "eval_steps_per_second": 5.748,
86
+ "step": 2000
87
+ },
88
+ {
89
+ "epoch": 1.2141816415735793,
90
+ "grad_norm": 17.49410629272461,
91
+ "learning_rate": 7.033571431701654e-05,
92
+ "loss": 0.5712,
93
+ "step": 2500
94
+ },
95
+ {
96
+ "epoch": 1.2141816415735793,
97
+ "eval_accuracy": 0.7101274957902334,
98
+ "eval_f1_macro": 0.6578185186923463,
99
+ "eval_loss": 1.0687695741653442,
100
+ "eval_precision_macro": 0.6947126776112352,
101
+ "eval_recall_macro": 0.6807690177369954,
102
+ "eval_runtime": 45.4304,
103
+ "eval_samples_per_second": 91.503,
104
+ "eval_steps_per_second": 5.723,
105
+ "step": 2500
106
+ },
107
+ {
108
+ "epoch": 1.4570179698882952,
109
+ "grad_norm": 14.797587394714355,
110
+ "learning_rate": 6.417297954733794e-05,
111
+ "loss": 0.5118,
112
+ "step": 3000
113
+ },
114
+ {
115
+ "epoch": 1.4570179698882952,
116
+ "eval_accuracy": 0.7466923261967765,
117
+ "eval_f1_macro": 0.6802785705299167,
118
+ "eval_loss": 0.9464945197105408,
119
+ "eval_precision_macro": 0.6962547831411214,
120
+ "eval_recall_macro": 0.7067511752266095,
121
+ "eval_runtime": 45.0782,
122
+ "eval_samples_per_second": 92.217,
123
+ "eval_steps_per_second": 5.768,
124
+ "step": 3000
125
+ },
126
+ {
127
+ "epoch": 1.6998542982030111,
128
+ "grad_norm": 11.592080116271973,
129
+ "learning_rate": 5.692862887331573e-05,
130
+ "loss": 0.4238,
131
+ "step": 3500
132
+ },
133
+ {
134
+ "epoch": 1.6998542982030111,
135
+ "eval_accuracy": 0.7529468366610537,
136
+ "eval_f1_macro": 0.6887735293131003,
137
+ "eval_loss": 1.0284276008605957,
138
+ "eval_precision_macro": 0.7004815690389604,
139
+ "eval_recall_macro": 0.7209895448469402,
140
+ "eval_runtime": 45.0958,
141
+ "eval_samples_per_second": 92.182,
142
+ "eval_steps_per_second": 5.766,
143
+ "step": 3500
144
+ },
145
+ {
146
+ "epoch": 1.942690626517727,
147
+ "grad_norm": 1.7279024124145508,
148
+ "learning_rate": 4.892680954747708e-05,
149
+ "loss": 0.383,
150
+ "step": 4000
151
+ },
152
+ {
153
+ "epoch": 1.942690626517727,
154
+ "eval_accuracy": 0.7784459947077219,
155
+ "eval_f1_macro": 0.7004470067611618,
156
+ "eval_loss": 0.9373700618743896,
157
+ "eval_precision_macro": 0.7012745858922871,
158
+ "eval_recall_macro": 0.7363165995805543,
159
+ "eval_runtime": 45.0166,
160
+ "eval_samples_per_second": 92.344,
161
+ "eval_steps_per_second": 5.776,
162
+ "step": 4000
163
+ },
164
+ {
165
+ "epoch": 2.1855269548324427,
166
+ "grad_norm": 11.464333534240723,
167
+ "learning_rate": 4.052556162978074e-05,
168
+ "loss": 0.2498,
169
+ "step": 4500
170
+ },
171
+ {
172
+ "epoch": 2.1855269548324427,
173
+ "eval_accuracy": 0.7897522251623768,
174
+ "eval_f1_macro": 0.736934271206392,
175
+ "eval_loss": 0.8516831398010254,
176
+ "eval_precision_macro": 0.7471052855094972,
177
+ "eval_recall_macro": 0.7513822718605427,
178
+ "eval_runtime": 45.2063,
179
+ "eval_samples_per_second": 91.956,
180
+ "eval_steps_per_second": 5.751,
181
+ "step": 4500
182
+ },
183
+ {
184
+ "epoch": 2.4283632831471587,
185
+ "grad_norm": 13.227448463439941,
186
+ "learning_rate": 3.2100797545350794e-05,
187
+ "loss": 0.2012,
188
+ "step": 5000
189
+ },
190
+ {
191
+ "epoch": 2.4283632831471587,
192
+ "eval_accuracy": 0.7952850613423141,
193
+ "eval_f1_macro": 0.7384644794255656,
194
+ "eval_loss": 0.8422956466674805,
195
+ "eval_precision_macro": 0.7407858112231859,
196
+ "eval_recall_macro": 0.7593629429944239,
197
+ "eval_runtime": 45.0668,
198
+ "eval_samples_per_second": 92.241,
199
+ "eval_steps_per_second": 5.769,
200
+ "step": 5000
201
+ },
202
+ {
203
+ "epoch": 2.6711996114618746,
204
+ "grad_norm": 14.610297203063965,
205
+ "learning_rate": 2.402948194623674e-05,
206
+ "loss": 0.1888,
207
+ "step": 5500
208
+ },
209
+ {
210
+ "epoch": 2.6711996114618746,
211
+ "eval_accuracy": 0.8383449603079144,
212
+ "eval_f1_macro": 0.7668856441209034,
213
+ "eval_loss": 0.7612192034721375,
214
+ "eval_precision_macro": 0.759848794474667,
215
+ "eval_recall_macro": 0.7875978932242379,
216
+ "eval_runtime": 44.9628,
217
+ "eval_samples_per_second": 92.454,
218
+ "eval_steps_per_second": 5.783,
219
+ "step": 5500
220
+ },
221
+ {
222
+ "epoch": 2.9140359397765905,
223
+ "grad_norm": 2.9459526538848877,
224
+ "learning_rate": 1.667276449145691e-05,
225
+ "loss": 0.1478,
226
+ "step": 6000
227
+ },
228
+ {
229
+ "epoch": 2.9140359397765905,
230
+ "eval_accuracy": 0.8284820784219389,
231
+ "eval_f1_macro": 0.7648949869466338,
232
+ "eval_loss": 0.7956407070159912,
233
+ "eval_precision_macro": 0.7582819516660327,
234
+ "eval_recall_macro": 0.7872534623468304,
235
+ "eval_runtime": 45.0026,
236
+ "eval_samples_per_second": 92.372,
237
+ "eval_steps_per_second": 5.777,
238
+ "step": 6000
239
+ },
240
+ {
241
+ "epoch": 3.1568722680913064,
242
+ "grad_norm": 0.04966867342591286,
243
+ "learning_rate": 1.035982026624521e-05,
244
+ "loss": 0.0805,
245
+ "step": 6500
246
+ },
247
+ {
248
+ "epoch": 3.1568722680913064,
249
+ "eval_accuracy": 0.8397883088765937,
250
+ "eval_f1_macro": 0.779163123362359,
251
+ "eval_loss": 0.7845637798309326,
252
+ "eval_precision_macro": 0.7736785485737475,
253
+ "eval_recall_macro": 0.7972932500440235,
254
+ "eval_runtime": 44.623,
255
+ "eval_samples_per_second": 93.158,
256
+ "eval_steps_per_second": 5.827,
257
+ "step": 6500
258
+ },
259
+ {
260
+ "epoch": 3.3997085964060223,
261
+ "grad_norm": 0.054828643798828125,
262
+ "learning_rate": 5.373120898224163e-06,
263
+ "loss": 0.054,
264
+ "step": 7000
265
+ },
266
+ {
267
+ "epoch": 3.3997085964060223,
268
+ "eval_accuracy": 0.8390666345922541,
269
+ "eval_f1_macro": 0.7789886096417518,
270
+ "eval_loss": 0.8231712579727173,
271
+ "eval_precision_macro": 0.7722144919792829,
272
+ "eval_recall_macro": 0.7985903156380745,
273
+ "eval_runtime": 44.6487,
274
+ "eval_samples_per_second": 93.105,
275
+ "eval_steps_per_second": 5.823,
276
+ "step": 7000
277
+ },
278
+ {
279
+ "epoch": 3.642544924720738,
280
+ "grad_norm": 8.141491889953613,
281
+ "learning_rate": 1.935795411934156e-06,
282
+ "loss": 0.0683,
283
+ "step": 7500
284
+ },
285
+ {
286
+ "epoch": 3.642544924720738,
287
+ "eval_accuracy": 0.8448400288669714,
288
+ "eval_f1_macro": 0.7842453714436081,
289
+ "eval_loss": 0.7753947377204895,
290
+ "eval_precision_macro": 0.7754804853445821,
291
+ "eval_recall_macro": 0.8051232260351716,
292
+ "eval_runtime": 45.7414,
293
+ "eval_samples_per_second": 90.881,
294
+ "eval_steps_per_second": 5.684,
295
+ "step": 7500
296
+ },
297
+ {
298
+ "epoch": 3.885381253035454,
299
+ "grad_norm": 4.538354873657227,
300
+ "learning_rate": 2.0164635815698608e-07,
301
+ "loss": 0.0531,
302
+ "step": 8000
303
+ },
304
+ {
305
+ "epoch": 3.885381253035454,
306
+ "eval_accuracy": 0.8462833774356507,
307
+ "eval_f1_macro": 0.7836126243666646,
308
+ "eval_loss": 0.778516948223114,
309
+ "eval_precision_macro": 0.773015814199716,
310
+ "eval_recall_macro": 0.8048624371833594,
311
+ "eval_runtime": 45.7139,
312
+ "eval_samples_per_second": 90.935,
313
+ "eval_steps_per_second": 5.688,
314
+ "step": 8000
315
+ }
316
+ ],
317
+ "logging_steps": 500,
318
+ "max_steps": 8236,
319
+ "num_input_tokens_seen": 0,
320
+ "num_train_epochs": 4,
321
+ "save_steps": 500,
322
+ "stateful_callbacks": {
323
+ "TrainerControl": {
324
+ "args": {
325
+ "should_epoch_stop": false,
326
+ "should_evaluate": false,
327
+ "should_log": false,
328
+ "should_save": true,
329
+ "should_training_stop": true
330
+ },
331
+ "attributes": {}
332
+ }
333
+ },
334
+ "total_flos": 1.7460348542595072e+16,
335
+ "train_batch_size": 16,
336
+ "trial_name": null,
337
+ "trial_params": null
338
+ }
checkpoint-8236/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c62d5b95ae007f7f68dfb168685d5940013d7e1bd191a6beea90ad5b2a515d2
3
+ size 5304
checkpoint-8236/vocab.txt ADDED
The diff for this file is too large to render. See raw diff