Hugging Face's logo

batoulnn
/
arabert_author_style_class5

Safetensors
Model card Files
xet
 Community
batoulnn commited on
Commit
586ae4d
·
verified ·
1 Parent(s): 820704c

Upload folder using huggingface_hub

Browse files
Files changed (24) hide show
  1. checkpoint-16000/config.json +70 -0
  2. checkpoint-16000/model.safetensors +3 -0
  3. checkpoint-16000/optimizer.pt +3 -0
  4. checkpoint-16000/rng_state.pth +3 -0
  5. checkpoint-16000/scaler.pt +3 -0
  6. checkpoint-16000/scheduler.pt +3 -0
  7. checkpoint-16000/special_tokens_map.json +37 -0
  8. checkpoint-16000/tokenizer.json +0 -0
  9. checkpoint-16000/tokenizer_config.json +339 -0
  10. checkpoint-16000/trainer_state.json +738 -0
  11. checkpoint-16000/training_args.bin +3 -0
  12. checkpoint-16000/vocab.txt +0 -0
  13. checkpoint-16472/config.json +70 -0
  14. checkpoint-16472/model.safetensors +3 -0
  15. checkpoint-16472/optimizer.pt +3 -0
  16. checkpoint-16472/rng_state.pth +3 -0
  17. checkpoint-16472/scaler.pt +3 -0
  18. checkpoint-16472/scheduler.pt +3 -0
  19. checkpoint-16472/special_tokens_map.json +37 -0
  20. checkpoint-16472/tokenizer.json +0 -0
  21. checkpoint-16472/tokenizer_config.json +339 -0
  22. checkpoint-16472/trainer_state.json +738 -0
  23. checkpoint-16472/training_args.bin +3 -0
  24. checkpoint-16472/vocab.txt +0 -0
checkpoint-16000/config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CustomAraBERTClassifier"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
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
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1,
38
+ "LABEL_10": 10,
39
+ "LABEL_11": 11,
40
+ "LABEL_12": 12,
41
+ "LABEL_13": 13,
42
+ "LABEL_14": 14,
43
+ "LABEL_15": 15,
44
+ "LABEL_16": 16,
45
+ "LABEL_17": 17,
46
+ "LABEL_18": 18,
47
+ "LABEL_19": 19,
48
+ "LABEL_2": 2,
49
+ "LABEL_20": 20,
50
+ "LABEL_3": 3,
51
+ "LABEL_4": 4,
52
+ "LABEL_5": 5,
53
+ "LABEL_6": 6,
54
+ "LABEL_7": 7,
55
+ "LABEL_8": 8,
56
+ "LABEL_9": 9
57
+ },
58
+ "layer_norm_eps": 1e-12,
59
+ "max_position_embeddings": 512,
60
+ "model_type": "bert",
61
+ "num_attention_heads": 12,
62
+ "num_hidden_layers": 12,
63
+ "pad_token_id": 0,
64
+ "position_embedding_type": "absolute",
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.53.3",
67
+ "type_vocab_size": 2,
68
+ "use_cache": true,
69
+ "vocab_size": 64000
70
+ }
checkpoint-16000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1cfe95ae476ebae01eb7cb5ecf8f37846b67859ba0267859299a2cdf714b399
3
+ size 542010628
checkpoint-16000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb00b19400d02fee8a13cc4c0810fa0ed7324349f319747ecf0063b5cce893c7
3
+ size 1084144011
checkpoint-16000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1fe1f75f395a62e73d8b166c6ec1537bb14584fa1c11d15f4d58a52f9e3dbdc
3
+ size 14645
checkpoint-16000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa0485828c43c408a2a183a8b6c2b05da427f0d417234a937d21bbc2ea20946f
3
+ size 1383
checkpoint-16000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b773be15703f8be28eaa65dec9520074661c7dfc1d7a97bef0b882c2b56b0f4
3
+ size 1465
checkpoint-16000/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-16000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-16000/tokenizer_config.json ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "+ا",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": true,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "+ك",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": true,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "ب+",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": true,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "+هم",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": true,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "+ات",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": true,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "+ي",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": true,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "ل+",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": true,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "+هما",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": true,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "+نا",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": true,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "+ن",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": true,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "+ها",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": true,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "+كما",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": true,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "+ة",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": true,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "ف+",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": true,
113
+ "special": true
114
+ },
115
+ "14": {
116
+ "content": "+كم",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": true,
121
+ "special": true
122
+ },
123
+ "15": {
124
+ "content": "+كن",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": true,
129
+ "special": true
130
+ },
131
+ "16": {
132
+ "content": "+ت",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": true,
137
+ "special": true
138
+ },
139
+ "17": {
140
+ "content": "[بريد]",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": true,
145
+ "special": true
146
+ },
147
+ "18": {
148
+ "content": "[مستخدم]",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": true,
153
+ "special": true
154
+ },
155
+ "19": {
156
+ "content": "لل+",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": true,
161
+ "special": true
162
+ },
163
+ "20": {
164
+ "content": "ال+",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": true,
169
+ "special": true
170
+ },
171
+ "21": {
172
+ "content": "[رابط]",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": true,
177
+ "special": true
178
+ },
179
+ "22": {
180
+ "content": "س+",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": true,
185
+ "special": true
186
+ },
187
+ "23": {
188
+ "content": "+ان",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": true,
193
+ "special": true
194
+ },
195
+ "24": {
196
+ "content": "+وا",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": true,
201
+ "special": true
202
+ },
203
+ "25": {
204
+ "content": "+ه",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": true,
209
+ "special": true
210
+ },
211
+ "26": {
212
+ "content": "+ون",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": true,
217
+ "special": true
218
+ },
219
+ "27": {
220
+ "content": "+هن",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": true,
225
+ "special": true
226
+ },
227
+ "28": {
228
+ "content": "+ين",
229
+ "lstrip": false,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": true,
233
+ "special": true
234
+ },
235
+ "29": {
236
+ "content": "��+",
237
+ "lstrip": false,
238
+ "normalized": true,
239
+ "rstrip": false,
240
+ "single_word": true,
241
+ "special": true
242
+ },
243
+ "30": {
244
+ "content": "ك+",
245
+ "lstrip": false,
246
+ "normalized": true,
247
+ "rstrip": false,
248
+ "single_word": true,
249
+ "special": true
250
+ },
251
+ "31": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32": {
260
+ "content": "[UNK]",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "33": {
268
+ "content": "[CLS]",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "34": {
276
+ "content": "[SEP]",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "35": {
284
+ "content": "[MASK]",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ }
291
+ },
292
+ "clean_up_tokenization_spaces": false,
293
+ "cls_token": "[CLS]",
294
+ "do_basic_tokenize": true,
295
+ "do_lower_case": false,
296
+ "extra_special_tokens": {},
297
+ "mask_token": "[MASK]",
298
+ "max_len": 512,
299
+ "model_max_length": 512,
300
+ "never_split": [
301
+ "+ك",
302
+ "+كما",
303
+ "ك+",
304
+ "+وا",
305
+ "+ين",
306
+ "و+",
307
+ "+كن",
308
+ "+ان",
309
+ "+هم",
310
+ "+ة",
311
+ "[بريد]",
312
+ "لل+",
313
+ "+ي",
314
+ "+ت",
315
+ "+ن",
316
+ "س+",
317
+ "ل+",
318
+ "[مستخدم]",
319
+ "+كم",
320
+ "+ا",
321
+ "ب+",
322
+ "ف+",
323
+ "+نا",
324
+ "+ها",
325
+ "+ون",
326
+ "+هما",
327
+ "ال+",
328
+ "+ه",
329
+ "+هن",
330
+ "+ات",
331
+ "[رابط]"
332
+ ],
333
+ "pad_token": "[PAD]",
334
+ "sep_token": "[SEP]",
335
+ "strip_accents": null,
336
+ "tokenize_chinese_chars": true,
337
+ "tokenizer_class": "BertTokenizer",
338
+ "unk_token": "[UNK]"
339
+ }
checkpoint-16000/trainer_state.json ADDED
@@ -0,0 +1,738 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 16000,
3
+ "best_metric": 0.8388668685961359,
4
+ "best_model_checkpoint": "./arabert_author_model/checkpoint-16000",
5
+ "epoch": 3.885381253035454,
6
+ "eval_steps": 500,
7
+ "global_step": 16000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.12141816415735794,
14
+ "grad_norm": 13.817139625549316,
15
+ "learning_rate": 2.393203883495146e-05,
16
+ "loss": 2.8517,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.12141816415735794,
21
+ "eval_accuracy": 0.3591532355063748,
22
+ "eval_f1_macro": 0.2494861292218586,
23
+ "eval_f1_micro": 0.3591532355063748,
24
+ "eval_loss": 2.5372836589813232,
25
+ "eval_precision_macro": 0.3073920888476956,
26
+ "eval_precision_micro": 0.3591532355063748,
27
+ "eval_recall_macro": 0.32410028025019516,
28
+ "eval_recall_micro": 0.3591532355063748,
29
+ "eval_runtime": 10.9588,
30
+ "eval_samples_per_second": 379.329,
31
+ "eval_steps_per_second": 47.45,
32
+ "step": 500
33
+ },
34
+ {
35
+ "epoch": 0.24283632831471588,
36
+ "grad_norm": 10.415640830993652,
37
+ "learning_rate": 4.820388349514564e-05,
38
+ "loss": 2.0655,
39
+ "step": 1000
40
+ },
41
+ {
42
+ "epoch": 0.24283632831471588,
43
+ "eval_accuracy": 0.5850372865046909,
44
+ "eval_f1_macro": 0.4679769319113009,
45
+ "eval_f1_micro": 0.5850372865046909,
46
+ "eval_loss": 1.5222690105438232,
47
+ "eval_precision_macro": 0.4891684038963785,
48
+ "eval_precision_micro": 0.5850372865046909,
49
+ "eval_recall_macro": 0.5299334368933829,
50
+ "eval_recall_micro": 0.5850372865046909,
51
+ "eval_runtime": 10.9419,
52
+ "eval_samples_per_second": 379.914,
53
+ "eval_steps_per_second": 47.524,
54
+ "step": 1000
55
+ },
56
+ {
57
+ "epoch": 0.3642544924720738,
58
+ "grad_norm": 33.21428298950195,
59
+ "learning_rate": 7.242718446601942e-05,
60
+ "loss": 1.3532,
61
+ "step": 1500
62
+ },
63
+ {
64
+ "epoch": 0.3642544924720738,
65
+ "eval_accuracy": 0.6062063988453211,
66
+ "eval_f1_macro": 0.5024409338775493,
67
+ "eval_f1_micro": 0.6062063988453211,
68
+ "eval_loss": 1.3000067472457886,
69
+ "eval_precision_macro": 0.5832350200281127,
70
+ "eval_precision_micro": 0.6062063988453211,
71
+ "eval_recall_macro": 0.556062953023934,
72
+ "eval_recall_micro": 0.6062063988453211,
73
+ "eval_runtime": 10.9618,
74
+ "eval_samples_per_second": 379.226,
75
+ "eval_steps_per_second": 47.437,
76
+ "step": 1500
77
+ },
78
+ {
79
+ "epoch": 0.48567265662943176,
80
+ "grad_norm": 9.017403602600098,
81
+ "learning_rate": 7.989375134121083e-05,
82
+ "loss": 1.0573,
83
+ "step": 2000
84
+ },
85
+ {
86
+ "epoch": 0.48567265662943176,
87
+ "eval_accuracy": 0.743565070964638,
88
+ "eval_f1_macro": 0.661667124930605,
89
+ "eval_f1_micro": 0.743565070964638,
90
+ "eval_loss": 0.9593473672866821,
91
+ "eval_precision_macro": 0.7070223201821213,
92
+ "eval_precision_micro": 0.743565070964638,
93
+ "eval_recall_macro": 0.6703159859068994,
94
+ "eval_recall_micro": 0.743565070964638,
95
+ "eval_runtime": 10.9878,
96
+ "eval_samples_per_second": 378.329,
97
+ "eval_steps_per_second": 47.325,
98
+ "step": 2000
99
+ },
100
+ {
101
+ "epoch": 0.6070908207867897,
102
+ "grad_norm": 39.439300537109375,
103
+ "learning_rate": 7.936184577251333e-05,
104
+ "loss": 0.8902,
105
+ "step": 2500
106
+ },
107
+ {
108
+ "epoch": 0.6070908207867897,
109
+ "eval_accuracy": 0.708684147221554,
110
+ "eval_f1_macro": 0.641807588675107,
111
+ "eval_f1_micro": 0.708684147221554,
112
+ "eval_loss": 1.1672111749649048,
113
+ "eval_precision_macro": 0.6949846119015083,
114
+ "eval_precision_micro": 0.708684147221554,
115
+ "eval_recall_macro": 0.6660911023131998,
116
+ "eval_recall_micro": 0.708684147221554,
117
+ "eval_runtime": 10.9685,
118
+ "eval_samples_per_second": 378.994,
119
+ "eval_steps_per_second": 47.408,
120
+ "step": 2500
121
+ },
122
+ {
123
+ "epoch": 0.7285089849441476,
124
+ "grad_norm": 15.976033210754395,
125
+ "learning_rate": 7.838839212672895e-05,
126
+ "loss": 0.7722,
127
+ "step": 3000
128
+ },
129
+ {
130
+ "epoch": 0.7285089849441476,
131
+ "eval_accuracy": 0.7815732499398604,
132
+ "eval_f1_macro": 0.6805898322013341,
133
+ "eval_f1_micro": 0.7815732499398604,
134
+ "eval_loss": 0.9774621725082397,
135
+ "eval_precision_macro": 0.681933497297422,
136
+ "eval_precision_micro": 0.7815732499398604,
137
+ "eval_recall_macro": 0.7037130745741084,
138
+ "eval_recall_micro": 0.7815732499398604,
139
+ "eval_runtime": 10.9775,
140
+ "eval_samples_per_second": 378.682,
141
+ "eval_steps_per_second": 47.369,
142
+ "step": 3000
143
+ },
144
+ {
145
+ "epoch": 0.8499271491015056,
146
+ "grad_norm": 13.439892768859863,
147
+ "learning_rate": 7.698431028266403e-05,
148
+ "loss": 0.6605,
149
+ "step": 3500
150
+ },
151
+ {
152
+ "epoch": 0.8499271491015056,
153
+ "eval_accuracy": 0.7654558575896079,
154
+ "eval_f1_macro": 0.6894780822997445,
155
+ "eval_f1_micro": 0.7654558575896079,
156
+ "eval_loss": 1.0220192670822144,
157
+ "eval_precision_macro": 0.7076718505110567,
158
+ "eval_precision_micro": 0.7654558575896079,
159
+ "eval_recall_macro": 0.7260098939240385,
160
+ "eval_recall_micro": 0.7654558575896079,
161
+ "eval_runtime": 10.9731,
162
+ "eval_samples_per_second": 378.836,
163
+ "eval_steps_per_second": 47.389,
164
+ "step": 3500
165
+ },
166
+ {
167
+ "epoch": 0.9713453132588635,
168
+ "grad_norm": 20.09202766418457,
169
+ "learning_rate": 7.516535076283984e-05,
170
+ "loss": 0.628,
171
+ "step": 4000
172
+ },
173
+ {
174
+ "epoch": 0.9713453132588635,
175
+ "eval_accuracy": 0.7916766899206158,
176
+ "eval_f1_macro": 0.6778803267216764,
177
+ "eval_f1_micro": 0.7916766899206158,
178
+ "eval_loss": 0.9702656269073486,
179
+ "eval_precision_macro": 0.7151431879177634,
180
+ "eval_precision_micro": 0.7916766899206158,
181
+ "eval_recall_macro": 0.7011458309909235,
182
+ "eval_recall_micro": 0.7916766899206158,
183
+ "eval_runtime": 10.9658,
184
+ "eval_samples_per_second": 379.088,
185
+ "eval_steps_per_second": 47.42,
186
+ "step": 4000
187
+ },
188
+ {
189
+ "epoch": 1.0927634774162214,
190
+ "grad_norm": 172.94845581054688,
191
+ "learning_rate": 7.295672280620509e-05,
192
+ "loss": 0.5502,
193
+ "step": 4500
194
+ },
195
+ {
196
+ "epoch": 1.0927634774162214,
197
+ "eval_accuracy": 0.7919172480153958,
198
+ "eval_f1_macro": 0.6957819662499832,
199
+ "eval_f1_micro": 0.7919172480153958,
200
+ "eval_loss": 1.2892016172409058,
201
+ "eval_precision_macro": 0.7464054287468073,
202
+ "eval_precision_micro": 0.7919172480153958,
203
+ "eval_recall_macro": 0.7183926804593861,
204
+ "eval_recall_micro": 0.7919172480153958,
205
+ "eval_runtime": 10.9635,
206
+ "eval_samples_per_second": 379.169,
207
+ "eval_steps_per_second": 47.43,
208
+ "step": 4500
209
+ },
210
+ {
211
+ "epoch": 1.2141816415735793,
212
+ "grad_norm": 203.87509155273438,
213
+ "learning_rate": 7.037435815032454e-05,
214
+ "loss": 0.4406,
215
+ "step": 5000
216
+ },
217
+ {
218
+ "epoch": 1.2141816415735793,
219
+ "eval_accuracy": 0.7570363242723117,
220
+ "eval_f1_macro": 0.6814189298571549,
221
+ "eval_f1_micro": 0.7570363242723117,
222
+ "eval_loss": 1.303400993347168,
223
+ "eval_precision_macro": 0.6973642430073081,
224
+ "eval_precision_micro": 0.7570363242723117,
225
+ "eval_recall_macro": 0.7124908812551407,
226
+ "eval_recall_micro": 0.7570363242723117,
227
+ "eval_runtime": 11.0017,
228
+ "eval_samples_per_second": 377.851,
229
+ "eval_steps_per_second": 47.265,
230
+ "step": 5000
231
+ },
232
+ {
233
+ "epoch": 1.3355998057309373,
234
+ "grad_norm": 0.6460123062133789,
235
+ "learning_rate": 6.74512640603739e-05,
236
+ "loss": 0.519,
237
+ "step": 5500
238
+ },
239
+ {
240
+ "epoch": 1.3355998057309373,
241
+ "eval_accuracy": 0.7827760404137599,
242
+ "eval_f1_macro": 0.7094534682279328,
243
+ "eval_f1_micro": 0.7827760404137599,
244
+ "eval_loss": 1.209078073501587,
245
+ "eval_precision_macro": 0.7201329832289568,
246
+ "eval_precision_micro": 0.7827760404137599,
247
+ "eval_recall_macro": 0.736328566738048,
248
+ "eval_recall_micro": 0.7827760404137599,
249
+ "eval_runtime": 10.9557,
250
+ "eval_samples_per_second": 379.437,
251
+ "eval_steps_per_second": 47.464,
252
+ "step": 5500
253
+ },
254
+ {
255
+ "epoch": 1.4570179698882952,
256
+ "grad_norm": 31.10455894470215,
257
+ "learning_rate": 6.42202308323677e-05,
258
+ "loss": 0.4404,
259
+ "step": 6000
260
+ },
261
+ {
262
+ "epoch": 1.4570179698882952,
263
+ "eval_accuracy": 0.8219870098628819,
264
+ "eval_f1_macro": 0.7542030095306345,
265
+ "eval_f1_micro": 0.8219870098628819,
266
+ "eval_loss": 1.026336908340454,
267
+ "eval_precision_macro": 0.7576623753992426,
268
+ "eval_precision_micro": 0.8219870098628819,
269
+ "eval_recall_macro": 0.7925456800333246,
270
+ "eval_recall_micro": 0.8219870098628819,
271
+ "eval_runtime": 10.9685,
272
+ "eval_samples_per_second": 378.993,
273
+ "eval_steps_per_second": 47.408,
274
+ "step": 6000
275
+ },
276
+ {
277
+ "epoch": 1.5784361340456532,
278
+ "grad_norm": 1.794871211051941,
279
+ "learning_rate": 6.0717503121017445e-05,
280
+ "loss": 0.3789,
281
+ "step": 6500
282
+ },
283
+ {
284
+ "epoch": 1.5784361340456532,
285
+ "eval_accuracy": 0.8542217945633871,
286
+ "eval_f1_macro": 0.7787297552725382,
287
+ "eval_f1_micro": 0.8542217945633871,
288
+ "eval_loss": 0.8210395574569702,
289
+ "eval_precision_macro": 0.8034809592650944,
290
+ "eval_precision_micro": 0.8542217945633871,
291
+ "eval_recall_macro": 0.7731802437378531,
292
+ "eval_recall_micro": 0.8542217945633871,
293
+ "eval_runtime": 10.9547,
294
+ "eval_samples_per_second": 379.473,
295
+ "eval_steps_per_second": 47.468,
296
+ "step": 6500
297
+ },
298
+ {
299
+ "epoch": 1.6998542982030111,
300
+ "grad_norm": 34.32925033569336,
301
+ "learning_rate": 5.69823733592655e-05,
302
+ "loss": 0.3734,
303
+ "step": 7000
304
+ },
305
+ {
306
+ "epoch": 1.6998542982030111,
307
+ "eval_accuracy": 0.7806110175607409,
308
+ "eval_f1_macro": 0.699900993601756,
309
+ "eval_f1_micro": 0.7806110175607409,
310
+ "eval_loss": 1.3878446817398071,
311
+ "eval_precision_macro": 0.7723533425562882,
312
+ "eval_precision_micro": 0.7806110175607409,
313
+ "eval_recall_macro": 0.6948437817490168,
314
+ "eval_recall_micro": 0.7806110175607409,
315
+ "eval_runtime": 10.9677,
316
+ "eval_samples_per_second": 379.023,
317
+ "eval_steps_per_second": 47.412,
318
+ "step": 7000
319
+ },
320
+ {
321
+ "epoch": 1.821272462360369,
322
+ "grad_norm": 0.0333857387304306,
323
+ "learning_rate": 5.305674098885817e-05,
324
+ "loss": 0.3417,
325
+ "step": 7500
326
+ },
327
+ {
328
+ "epoch": 1.821272462360369,
329
+ "eval_accuracy": 0.8414722155400529,
330
+ "eval_f1_macro": 0.752167782578507,
331
+ "eval_f1_micro": 0.8414722155400529,
332
+ "eval_loss": 0.9198834896087646,
333
+ "eval_precision_macro": 0.7597509711251361,
334
+ "eval_precision_micro": 0.8414722155400529,
335
+ "eval_recall_macro": 0.7664744721724374,
336
+ "eval_recall_micro": 0.8414722155400529,
337
+ "eval_runtime": 10.9665,
338
+ "eval_samples_per_second": 379.065,
339
+ "eval_steps_per_second": 47.417,
340
+ "step": 7500
341
+ },
342
+ {
343
+ "epoch": 1.942690626517727,
344
+ "grad_norm": 0.03518730029463768,
345
+ "learning_rate": 4.8984642446361996e-05,
346
+ "loss": 0.342,
347
+ "step": 8000
348
+ },
349
+ {
350
+ "epoch": 1.942690626517727,
351
+ "eval_accuracy": 0.821746451768102,
352
+ "eval_f1_macro": 0.738186135147291,
353
+ "eval_f1_micro": 0.821746451768102,
354
+ "eval_loss": 1.0331408977508545,
355
+ "eval_precision_macro": 0.7592295903512796,
356
+ "eval_precision_micro": 0.821746451768102,
357
+ "eval_recall_macro": 0.7439263957407788,
358
+ "eval_recall_micro": 0.821746451768102,
359
+ "eval_runtime": 11.0024,
360
+ "eval_samples_per_second": 377.826,
361
+ "eval_steps_per_second": 47.262,
362
+ "step": 8000
363
+ },
364
+ {
365
+ "epoch": 2.064108790675085,
366
+ "grad_norm": 0.18279767036437988,
367
+ "learning_rate": 4.481175717708393e-05,
368
+ "loss": 0.2898,
369
+ "step": 8500
370
+ },
371
+ {
372
+ "epoch": 2.064108790675085,
373
+ "eval_accuracy": 0.8203031031994227,
374
+ "eval_f1_macro": 0.7478170717551785,
375
+ "eval_f1_micro": 0.8203031031994227,
376
+ "eval_loss": 1.1277570724487305,
377
+ "eval_precision_macro": 0.7730855406484367,
378
+ "eval_precision_micro": 0.8203031031994227,
379
+ "eval_recall_macro": 0.7543267040014913,
380
+ "eval_recall_micro": 0.8203031031994227,
381
+ "eval_runtime": 10.9448,
382
+ "eval_samples_per_second": 379.815,
383
+ "eval_steps_per_second": 47.511,
384
+ "step": 8500
385
+ },
386
+ {
387
+ "epoch": 2.1855269548324427,
388
+ "grad_norm": 0.01960030198097229,
389
+ "learning_rate": 4.058489521826674e-05,
390
+ "loss": 0.1742,
391
+ "step": 9000
392
+ },
393
+ {
394
+ "epoch": 2.1855269548324427,
395
+ "eval_accuracy": 0.8419533317296127,
396
+ "eval_f1_macro": 0.7694964141590861,
397
+ "eval_f1_micro": 0.8419533317296127,
398
+ "eval_loss": 1.0578076839447021,
399
+ "eval_precision_macro": 0.7655705311822759,
400
+ "eval_precision_micro": 0.8419533317296127,
401
+ "eval_recall_macro": 0.7997867857803433,
402
+ "eval_recall_micro": 0.8419533317296127,
403
+ "eval_runtime": 11.1045,
404
+ "eval_samples_per_second": 374.354,
405
+ "eval_steps_per_second": 46.828,
406
+ "step": 9000
407
+ },
408
+ {
409
+ "epoch": 2.306945118989801,
410
+ "grad_norm": 1.8985679149627686,
411
+ "learning_rate": 3.635147209968037e-05,
412
+ "loss": 0.2277,
413
+ "step": 9500
414
+ },
415
+ {
416
+ "epoch": 2.306945118989801,
417
+ "eval_accuracy": 0.8551840269425066,
418
+ "eval_f1_macro": 0.8010324516227308,
419
+ "eval_f1_micro": 0.8551840269425066,
420
+ "eval_loss": 0.95162034034729,
421
+ "eval_precision_macro": 0.7994379036468637,
422
+ "eval_precision_micro": 0.8551840269425066,
423
+ "eval_recall_macro": 0.8284130356636192,
424
+ "eval_recall_micro": 0.8551840269425066,
425
+ "eval_runtime": 10.9658,
426
+ "eval_samples_per_second": 379.089,
427
+ "eval_steps_per_second": 47.42,
428
+ "step": 9500
429
+ },
430
+ {
431
+ "epoch": 2.4283632831471587,
432
+ "grad_norm": 0.08672552555799484,
433
+ "learning_rate": 3.215897695200002e-05,
434
+ "loss": 0.1459,
435
+ "step": 10000
436
+ },
437
+ {
438
+ "epoch": 2.4283632831471587,
439
+ "eval_accuracy": 0.8580707240798653,
440
+ "eval_f1_macro": 0.7735650259965305,
441
+ "eval_f1_micro": 0.8580707240798653,
442
+ "eval_loss": 0.9313622713088989,
443
+ "eval_precision_macro": 0.8197415932054871,
444
+ "eval_precision_micro": 0.8580707240798653,
445
+ "eval_recall_macro": 0.774173537961469,
446
+ "eval_recall_micro": 0.8580707240798653,
447
+ "eval_runtime": 11.0033,
448
+ "eval_samples_per_second": 377.797,
449
+ "eval_steps_per_second": 47.259,
450
+ "step": 10000
451
+ },
452
+ {
453
+ "epoch": 2.549781447304517,
454
+ "grad_norm": 0.010399931110441685,
455
+ "learning_rate": 2.8062530261954673e-05,
456
+ "loss": 0.1634,
457
+ "step": 10500
458
+ },
459
+ {
460
+ "epoch": 2.549781447304517,
461
+ "eval_accuracy": 0.8443589126774116,
462
+ "eval_f1_macro": 0.7537922358196677,
463
+ "eval_f1_micro": 0.8443589126774116,
464
+ "eval_loss": 1.0135008096694946,
465
+ "eval_precision_macro": 0.8301941849742014,
466
+ "eval_precision_micro": 0.8443589126774116,
467
+ "eval_recall_macro": 0.7457995267519847,
468
+ "eval_recall_micro": 0.8443589126774116,
469
+ "eval_runtime": 11.0399,
470
+ "eval_samples_per_second": 376.542,
471
+ "eval_steps_per_second": 47.102,
472
+ "step": 10500
473
+ },
474
+ {
475
+ "epoch": 2.6711996114618746,
476
+ "grad_norm": 0.012511692009866238,
477
+ "learning_rate": 2.409168137642188e-05,
478
+ "loss": 0.151,
479
+ "step": 11000
480
+ },
481
+ {
482
+ "epoch": 2.6711996114618746,
483
+ "eval_accuracy": 0.8794803945152755,
484
+ "eval_f1_macro": 0.8238485237925146,
485
+ "eval_f1_micro": 0.8794803945152755,
486
+ "eval_loss": 0.798862636089325,
487
+ "eval_precision_macro": 0.8338077165115332,
488
+ "eval_precision_micro": 0.8794803945152755,
489
+ "eval_recall_macro": 0.8296556196318619,
490
+ "eval_recall_micro": 0.8794803945152755,
491
+ "eval_runtime": 11.0936,
492
+ "eval_samples_per_second": 374.72,
493
+ "eval_steps_per_second": 46.874,
494
+ "step": 11000
495
+ },
496
+ {
497
+ "epoch": 2.7926177756192327,
498
+ "grad_norm": 0.5942862033843994,
499
+ "learning_rate": 2.0299286711215096e-05,
500
+ "loss": 0.1627,
501
+ "step": 11500
502
+ },
503
+ {
504
+ "epoch": 2.7926177756192327,
505
+ "eval_accuracy": 0.8833293240317537,
506
+ "eval_f1_macro": 0.8258632320077727,
507
+ "eval_f1_micro": 0.8833293240317537,
508
+ "eval_loss": 0.7369428873062134,
509
+ "eval_precision_macro": 0.8208617314770252,
510
+ "eval_precision_micro": 0.8833293240317537,
511
+ "eval_recall_macro": 0.842352557212921,
512
+ "eval_recall_micro": 0.8833293240317537,
513
+ "eval_runtime": 11.0093,
514
+ "eval_samples_per_second": 377.589,
515
+ "eval_steps_per_second": 47.233,
516
+ "step": 11500
517
+ },
518
+ {
519
+ "epoch": 2.9140359397765905,
520
+ "grad_norm": 0.1483508050441742,
521
+ "learning_rate": 1.672788808669644e-05,
522
+ "loss": 0.1147,
523
+ "step": 12000
524
+ },
525
+ {
526
+ "epoch": 2.9140359397765905,
527
+ "eval_accuracy": 0.8607168631224441,
528
+ "eval_f1_macro": 0.8148434050055327,
529
+ "eval_f1_micro": 0.8607168631224441,
530
+ "eval_loss": 0.9235690236091614,
531
+ "eval_precision_macro": 0.8216220364551388,
532
+ "eval_precision_micro": 0.8607168631224441,
533
+ "eval_recall_macro": 0.8206810147792551,
534
+ "eval_recall_micro": 0.8607168631224441,
535
+ "eval_runtime": 10.9967,
536
+ "eval_samples_per_second": 378.023,
537
+ "eval_steps_per_second": 47.287,
538
+ "step": 12000
539
+ },
540
+ {
541
+ "epoch": 3.0354541039339487,
542
+ "grad_norm": 0.015476622618734837,
543
+ "learning_rate": 1.3417548263242596e-05,
544
+ "loss": 0.1495,
545
+ "step": 12500
546
+ },
547
+ {
548
+ "epoch": 3.0354541039339487,
549
+ "eval_accuracy": 0.8857349049795525,
550
+ "eval_f1_macro": 0.8348811939709606,
551
+ "eval_f1_micro": 0.8857349049795525,
552
+ "eval_loss": 0.7240191102027893,
553
+ "eval_precision_macro": 0.8269436011383359,
554
+ "eval_precision_micro": 0.8857349049795525,
555
+ "eval_recall_macro": 0.8585739727750367,
556
+ "eval_recall_micro": 0.8857349049795525,
557
+ "eval_runtime": 10.9994,
558
+ "eval_samples_per_second": 377.931,
559
+ "eval_steps_per_second": 47.275,
560
+ "step": 12500
561
+ },
562
+ {
563
+ "epoch": 3.1568722680913064,
564
+ "grad_norm": 0.003895299741998315,
565
+ "learning_rate": 1.040540153054102e-05,
566
+ "loss": 0.0428,
567
+ "step": 13000
568
+ },
569
+ {
570
+ "epoch": 3.1568722680913064,
571
+ "eval_accuracy": 0.8886216021169112,
572
+ "eval_f1_macro": 0.8320140900627028,
573
+ "eval_f1_micro": 0.8886216021169112,
574
+ "eval_loss": 0.7417625188827515,
575
+ "eval_precision_macro": 0.8215695976609916,
576
+ "eval_precision_micro": 0.8886216021169112,
577
+ "eval_recall_macro": 0.8562463713090399,
578
+ "eval_recall_micro": 0.8886216021169112,
579
+ "eval_runtime": 10.993,
580
+ "eval_samples_per_second": 378.15,
581
+ "eval_steps_per_second": 47.303,
582
+ "step": 13000
583
+ },
584
+ {
585
+ "epoch": 3.2782904322486646,
586
+ "grad_norm": 0.009999997913837433,
587
+ "learning_rate": 7.725237147495241e-06,
588
+ "loss": 0.0674,
589
+ "step": 13500
590
+ },
591
+ {
592
+ "epoch": 3.2782904322486646,
593
+ "eval_accuracy": 0.863122444070243,
594
+ "eval_f1_macro": 0.8141275248610652,
595
+ "eval_f1_micro": 0.863122444070243,
596
+ "eval_loss": 0.9269203543663025,
597
+ "eval_precision_macro": 0.8155994650555717,
598
+ "eval_precision_micro": 0.863122444070243,
599
+ "eval_recall_macro": 0.831120303176534,
600
+ "eval_recall_micro": 0.863122444070243,
601
+ "eval_runtime": 11.0377,
602
+ "eval_samples_per_second": 376.619,
603
+ "eval_steps_per_second": 47.111,
604
+ "step": 13500
605
+ },
606
+ {
607
+ "epoch": 3.3997085964060223,
608
+ "grad_norm": 0.002102572238072753,
609
+ "learning_rate": 5.411377224960022e-06,
610
+ "loss": 0.0348,
611
+ "step": 14000
612
+ },
613
+ {
614
+ "epoch": 3.3997085964060223,
615
+ "eval_accuracy": 0.8864565792638922,
616
+ "eval_f1_macro": 0.8278883555316573,
617
+ "eval_f1_micro": 0.8864565792638922,
618
+ "eval_loss": 0.7893477082252502,
619
+ "eval_precision_macro": 0.8234196007036506,
620
+ "eval_precision_micro": 0.8864565792638922,
621
+ "eval_recall_macro": 0.8436628954935477,
622
+ "eval_recall_micro": 0.8864565792638922,
623
+ "eval_runtime": 10.991,
624
+ "eval_samples_per_second": 378.217,
625
+ "eval_steps_per_second": 47.311,
626
+ "step": 14000
627
+ },
628
+ {
629
+ "epoch": 3.52112676056338,
630
+ "grad_norm": 0.0026018042117357254,
631
+ "learning_rate": 3.4805125817474373e-06,
632
+ "loss": 0.0429,
633
+ "step": 14500
634
+ },
635
+ {
636
+ "epoch": 3.52112676056338,
637
+ "eval_accuracy": 0.8883810440221314,
638
+ "eval_f1_macro": 0.8359878499067832,
639
+ "eval_f1_micro": 0.8883810440221314,
640
+ "eval_loss": 0.7969309091567993,
641
+ "eval_precision_macro": 0.8351453883280561,
642
+ "eval_precision_micro": 0.8883810440221314,
643
+ "eval_recall_macro": 0.8493998324444691,
644
+ "eval_recall_micro": 0.8883810440221314,
645
+ "eval_runtime": 10.9595,
646
+ "eval_samples_per_second": 379.305,
647
+ "eval_steps_per_second": 47.447,
648
+ "step": 14500
649
+ },
650
+ {
651
+ "epoch": 3.642544924720738,
652
+ "grad_norm": 0.005027813836932182,
653
+ "learning_rate": 1.9619328163448515e-06,
654
+ "loss": 0.0472,
655
+ "step": 15000
656
+ },
657
+ {
658
+ "epoch": 3.642544924720738,
659
+ "eval_accuracy": 0.8871782535482319,
660
+ "eval_f1_macro": 0.8293197008433407,
661
+ "eval_f1_micro": 0.8871782535482319,
662
+ "eval_loss": 0.7746603488922119,
663
+ "eval_precision_macro": 0.8285879613227065,
664
+ "eval_precision_micro": 0.8871782535482319,
665
+ "eval_recall_macro": 0.843758966912644,
666
+ "eval_recall_micro": 0.8871782535482319,
667
+ "eval_runtime": 10.9555,
668
+ "eval_samples_per_second": 379.444,
669
+ "eval_steps_per_second": 47.465,
670
+ "step": 15000
671
+ },
672
+ {
673
+ "epoch": 3.7639630888780964,
674
+ "grad_norm": 0.001474579912610352,
675
+ "learning_rate": 8.665920662387894e-07,
676
+ "loss": 0.0654,
677
+ "step": 15500
678
+ },
679
+ {
680
+ "epoch": 3.7639630888780964,
681
+ "eval_accuracy": 0.8878999278325715,
682
+ "eval_f1_macro": 0.8333706258627294,
683
+ "eval_f1_micro": 0.8878999278325715,
684
+ "eval_loss": 0.7646775841712952,
685
+ "eval_precision_macro": 0.8323851081178661,
686
+ "eval_precision_micro": 0.8878999278325715,
687
+ "eval_recall_macro": 0.8465412634330337,
688
+ "eval_recall_micro": 0.8878999278325715,
689
+ "eval_runtime": 11.0797,
690
+ "eval_samples_per_second": 375.191,
691
+ "eval_steps_per_second": 46.933,
692
+ "step": 15500
693
+ },
694
+ {
695
+ "epoch": 3.885381253035454,
696
+ "grad_norm": 0.02036176808178425,
697
+ "learning_rate": 2.1023685362179913e-07,
698
+ "loss": 0.0519,
699
+ "step": 16000
700
+ },
701
+ {
702
+ "epoch": 3.885381253035454,
703
+ "eval_accuracy": 0.8910271830647102,
704
+ "eval_f1_macro": 0.8388668685961359,
705
+ "eval_f1_micro": 0.8910271830647102,
706
+ "eval_loss": 0.7371587753295898,
707
+ "eval_precision_macro": 0.8351964171775984,
708
+ "eval_precision_micro": 0.8910271830647102,
709
+ "eval_recall_macro": 0.8528710223600782,
710
+ "eval_recall_micro": 0.8910271830647102,
711
+ "eval_runtime": 10.9604,
712
+ "eval_samples_per_second": 379.273,
713
+ "eval_steps_per_second": 47.443,
714
+ "step": 16000
715
+ }
716
+ ],
717
+ "logging_steps": 500,
718
+ "max_steps": 16472,
719
+ "num_input_tokens_seen": 0,
720
+ "num_train_epochs": 4,
721
+ "save_steps": 500,
722
+ "stateful_callbacks": {
723
+ "TrainerControl": {
724
+ "args": {
725
+ "should_epoch_stop": false,
726
+ "should_evaluate": false,
727
+ "should_log": false,
728
+ "should_save": true,
729
+ "should_training_stop": false
730
+ },
731
+ "attributes": {}
732
+ }
733
+ },
734
+ "total_flos": 3.3794528238314496e+16,
735
+ "train_batch_size": 8,
736
+ "trial_name": null,
737
+ "trial_params": null
738
+ }
checkpoint-16000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:733beefefbbbe74f348894313550142320fa88d841d14225798e6321192444dd
3
+ size 5713
checkpoint-16000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-16472/config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CustomAraBERTClassifier"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
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
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1,
38
+ "LABEL_10": 10,
39
+ "LABEL_11": 11,
40
+ "LABEL_12": 12,
41
+ "LABEL_13": 13,
42
+ "LABEL_14": 14,
43
+ "LABEL_15": 15,
44
+ "LABEL_16": 16,
45
+ "LABEL_17": 17,
46
+ "LABEL_18": 18,
47
+ "LABEL_19": 19,
48
+ "LABEL_2": 2,
49
+ "LABEL_20": 20,
50
+ "LABEL_3": 3,
51
+ "LABEL_4": 4,
52
+ "LABEL_5": 5,
53
+ "LABEL_6": 6,
54
+ "LABEL_7": 7,
55
+ "LABEL_8": 8,
56
+ "LABEL_9": 9
57
+ },
58
+ "layer_norm_eps": 1e-12,
59
+ "max_position_embeddings": 512,
60
+ "model_type": "bert",
61
+ "num_attention_heads": 12,
62
+ "num_hidden_layers": 12,
63
+ "pad_token_id": 0,
64
+ "position_embedding_type": "absolute",
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.53.3",
67
+ "type_vocab_size": 2,
68
+ "use_cache": true,
69
+ "vocab_size": 64000
70
+ }
checkpoint-16472/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ec236a778e11c71808f8f382bbea564dc251689138f26a86a51633def93684f
3
+ size 542010628
checkpoint-16472/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c535f7d717589689e599f9e767016cd85570f1f3f1db42999901719fa1ce0806
3
+ size 1084144011
checkpoint-16472/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0d2ab663d81d3221a8e31be1f7659d5f23c2b1d8964f3d4bf7cceef63104150
3
+ size 14645
checkpoint-16472/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc3da17bd085ed88c7ee60d15d27b7c3a39ca3eef71ef397340bae898a312171
3
+ size 1383
checkpoint-16472/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b3d7f8e7d240acd0b69140807523f5f3689ad5dc47bdbdc66da735019a3419b
3
+ size 1465
checkpoint-16472/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-16472/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-16472/tokenizer_config.json ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "+ا",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": true,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "+ك",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": true,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "ب+",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": true,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "+هم",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": true,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "+ات",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": true,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "+ي",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": true,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "ل+",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": true,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "+هما",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": true,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "+نا",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": true,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "+ن",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": true,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "+ها",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": true,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "+كما",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": true,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "+ة",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": true,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "ف+",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": true,
113
+ "special": true
114
+ },
115
+ "14": {
116
+ "content": "+كم",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": true,
121
+ "special": true
122
+ },
123
+ "15": {
124
+ "content": "+كن",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": true,
129
+ "special": true
130
+ },
131
+ "16": {
132
+ "content": "+ت",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": true,
137
+ "special": true
138
+ },
139
+ "17": {
140
+ "content": "[بريد]",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": true,
145
+ "special": true
146
+ },
147
+ "18": {
148
+ "content": "[مستخدم]",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": true,
153
+ "special": true
154
+ },
155
+ "19": {
156
+ "content": "لل+",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": true,
161
+ "special": true
162
+ },
163
+ "20": {
164
+ "content": "ال+",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": true,
169
+ "special": true
170
+ },
171
+ "21": {
172
+ "content": "[رابط]",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": true,
177
+ "special": true
178
+ },
179
+ "22": {
180
+ "content": "س+",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": true,
185
+ "special": true
186
+ },
187
+ "23": {
188
+ "content": "+ان",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": true,
193
+ "special": true
194
+ },
195
+ "24": {
196
+ "content": "+وا",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": true,
201
+ "special": true
202
+ },
203
+ "25": {
204
+ "content": "+ه",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": true,
209
+ "special": true
210
+ },
211
+ "26": {
212
+ "content": "+ون",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": true,
217
+ "special": true
218
+ },
219
+ "27": {
220
+ "content": "+هن",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": true,
225
+ "special": true
226
+ },
227
+ "28": {
228
+ "content": "+ين",
229
+ "lstrip": false,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": true,
233
+ "special": true
234
+ },
235
+ "29": {
236
+ "content": "��+",
237
+ "lstrip": false,
238
+ "normalized": true,
239
+ "rstrip": false,
240
+ "single_word": true,
241
+ "special": true
242
+ },
243
+ "30": {
244
+ "content": "ك+",
245
+ "lstrip": false,
246
+ "normalized": true,
247
+ "rstrip": false,
248
+ "single_word": true,
249
+ "special": true
250
+ },
251
+ "31": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32": {
260
+ "content": "[UNK]",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "33": {
268
+ "content": "[CLS]",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "34": {
276
+ "content": "[SEP]",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "35": {
284
+ "content": "[MASK]",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ }
291
+ },
292
+ "clean_up_tokenization_spaces": false,
293
+ "cls_token": "[CLS]",
294
+ "do_basic_tokenize": true,
295
+ "do_lower_case": false,
296
+ "extra_special_tokens": {},
297
+ "mask_token": "[MASK]",
298
+ "max_len": 512,
299
+ "model_max_length": 512,
300
+ "never_split": [
301
+ "+ك",
302
+ "+كما",
303
+ "ك+",
304
+ "+وا",
305
+ "+ين",
306
+ "و+",
307
+ "+كن",
308
+ "+ان",
309
+ "+هم",
310
+ "+ة",
311
+ "[بريد]",
312
+ "لل+",
313
+ "+ي",
314
+ "+ت",
315
+ "+ن",
316
+ "س+",
317
+ "ل+",
318
+ "[مستخدم]",
319
+ "+كم",
320
+ "+ا",
321
+ "ب+",
322
+ "ف+",
323
+ "+نا",
324
+ "+ها",
325
+ "+ون",
326
+ "+هما",
327
+ "ال+",
328
+ "+ه",
329
+ "+هن",
330
+ "+ات",
331
+ "[رابط]"
332
+ ],
333
+ "pad_token": "[PAD]",
334
+ "sep_token": "[SEP]",
335
+ "strip_accents": null,
336
+ "tokenize_chinese_chars": true,
337
+ "tokenizer_class": "BertTokenizer",
338
+ "unk_token": "[UNK]"
339
+ }
checkpoint-16472/trainer_state.json ADDED
@@ -0,0 +1,738 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 16000,
3
+ "best_metric": 0.8388668685961359,
4
+ "best_model_checkpoint": "./arabert_author_model/checkpoint-16000",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 16472,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.12141816415735794,
14
+ "grad_norm": 13.817139625549316,
15
+ "learning_rate": 2.393203883495146e-05,
16
+ "loss": 2.8517,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.12141816415735794,
21
+ "eval_accuracy": 0.3591532355063748,
22
+ "eval_f1_macro": 0.2494861292218586,
23
+ "eval_f1_micro": 0.3591532355063748,
24
+ "eval_loss": 2.5372836589813232,
25
+ "eval_precision_macro": 0.3073920888476956,
26
+ "eval_precision_micro": 0.3591532355063748,
27
+ "eval_recall_macro": 0.32410028025019516,
28
+ "eval_recall_micro": 0.3591532355063748,
29
+ "eval_runtime": 10.9588,
30
+ "eval_samples_per_second": 379.329,
31
+ "eval_steps_per_second": 47.45,
32
+ "step": 500
33
+ },
34
+ {
35
+ "epoch": 0.24283632831471588,
36
+ "grad_norm": 10.415640830993652,
37
+ "learning_rate": 4.820388349514564e-05,
38
+ "loss": 2.0655,
39
+ "step": 1000
40
+ },
41
+ {
42
+ "epoch": 0.24283632831471588,
43
+ "eval_accuracy": 0.5850372865046909,
44
+ "eval_f1_macro": 0.4679769319113009,
45
+ "eval_f1_micro": 0.5850372865046909,
46
+ "eval_loss": 1.5222690105438232,
47
+ "eval_precision_macro": 0.4891684038963785,
48
+ "eval_precision_micro": 0.5850372865046909,
49
+ "eval_recall_macro": 0.5299334368933829,
50
+ "eval_recall_micro": 0.5850372865046909,
51
+ "eval_runtime": 10.9419,
52
+ "eval_samples_per_second": 379.914,
53
+ "eval_steps_per_second": 47.524,
54
+ "step": 1000
55
+ },
56
+ {
57
+ "epoch": 0.3642544924720738,
58
+ "grad_norm": 33.21428298950195,
59
+ "learning_rate": 7.242718446601942e-05,
60
+ "loss": 1.3532,
61
+ "step": 1500
62
+ },
63
+ {
64
+ "epoch": 0.3642544924720738,
65
+ "eval_accuracy": 0.6062063988453211,
66
+ "eval_f1_macro": 0.5024409338775493,
67
+ "eval_f1_micro": 0.6062063988453211,
68
+ "eval_loss": 1.3000067472457886,
69
+ "eval_precision_macro": 0.5832350200281127,
70
+ "eval_precision_micro": 0.6062063988453211,
71
+ "eval_recall_macro": 0.556062953023934,
72
+ "eval_recall_micro": 0.6062063988453211,
73
+ "eval_runtime": 10.9618,
74
+ "eval_samples_per_second": 379.226,
75
+ "eval_steps_per_second": 47.437,
76
+ "step": 1500
77
+ },
78
+ {
79
+ "epoch": 0.48567265662943176,
80
+ "grad_norm": 9.017403602600098,
81
+ "learning_rate": 7.989375134121083e-05,
82
+ "loss": 1.0573,
83
+ "step": 2000
84
+ },
85
+ {
86
+ "epoch": 0.48567265662943176,
87
+ "eval_accuracy": 0.743565070964638,
88
+ "eval_f1_macro": 0.661667124930605,
89
+ "eval_f1_micro": 0.743565070964638,
90
+ "eval_loss": 0.9593473672866821,
91
+ "eval_precision_macro": 0.7070223201821213,
92
+ "eval_precision_micro": 0.743565070964638,
93
+ "eval_recall_macro": 0.6703159859068994,
94
+ "eval_recall_micro": 0.743565070964638,
95
+ "eval_runtime": 10.9878,
96
+ "eval_samples_per_second": 378.329,
97
+ "eval_steps_per_second": 47.325,
98
+ "step": 2000
99
+ },
100
+ {
101
+ "epoch": 0.6070908207867897,
102
+ "grad_norm": 39.439300537109375,
103
+ "learning_rate": 7.936184577251333e-05,
104
+ "loss": 0.8902,
105
+ "step": 2500
106
+ },
107
+ {
108
+ "epoch": 0.6070908207867897,
109
+ "eval_accuracy": 0.708684147221554,
110
+ "eval_f1_macro": 0.641807588675107,
111
+ "eval_f1_micro": 0.708684147221554,
112
+ "eval_loss": 1.1672111749649048,
113
+ "eval_precision_macro": 0.6949846119015083,
114
+ "eval_precision_micro": 0.708684147221554,
115
+ "eval_recall_macro": 0.6660911023131998,
116
+ "eval_recall_micro": 0.708684147221554,
117
+ "eval_runtime": 10.9685,
118
+ "eval_samples_per_second": 378.994,
119
+ "eval_steps_per_second": 47.408,
120
+ "step": 2500
121
+ },
122
+ {
123
+ "epoch": 0.7285089849441476,
124
+ "grad_norm": 15.976033210754395,
125
+ "learning_rate": 7.838839212672895e-05,
126
+ "loss": 0.7722,
127
+ "step": 3000
128
+ },
129
+ {
130
+ "epoch": 0.7285089849441476,
131
+ "eval_accuracy": 0.7815732499398604,
132
+ "eval_f1_macro": 0.6805898322013341,
133
+ "eval_f1_micro": 0.7815732499398604,
134
+ "eval_loss": 0.9774621725082397,
135
+ "eval_precision_macro": 0.681933497297422,
136
+ "eval_precision_micro": 0.7815732499398604,
137
+ "eval_recall_macro": 0.7037130745741084,
138
+ "eval_recall_micro": 0.7815732499398604,
139
+ "eval_runtime": 10.9775,
140
+ "eval_samples_per_second": 378.682,
141
+ "eval_steps_per_second": 47.369,
142
+ "step": 3000
143
+ },
144
+ {
145
+ "epoch": 0.8499271491015056,
146
+ "grad_norm": 13.439892768859863,
147
+ "learning_rate": 7.698431028266403e-05,
148
+ "loss": 0.6605,
149
+ "step": 3500
150
+ },
151
+ {
152
+ "epoch": 0.8499271491015056,
153
+ "eval_accuracy": 0.7654558575896079,
154
+ "eval_f1_macro": 0.6894780822997445,
155
+ "eval_f1_micro": 0.7654558575896079,
156
+ "eval_loss": 1.0220192670822144,
157
+ "eval_precision_macro": 0.7076718505110567,
158
+ "eval_precision_micro": 0.7654558575896079,
159
+ "eval_recall_macro": 0.7260098939240385,
160
+ "eval_recall_micro": 0.7654558575896079,
161
+ "eval_runtime": 10.9731,
162
+ "eval_samples_per_second": 378.836,
163
+ "eval_steps_per_second": 47.389,
164
+ "step": 3500
165
+ },
166
+ {
167
+ "epoch": 0.9713453132588635,
168
+ "grad_norm": 20.09202766418457,
169
+ "learning_rate": 7.516535076283984e-05,
170
+ "loss": 0.628,
171
+ "step": 4000
172
+ },
173
+ {
174
+ "epoch": 0.9713453132588635,
175
+ "eval_accuracy": 0.7916766899206158,
176
+ "eval_f1_macro": 0.6778803267216764,
177
+ "eval_f1_micro": 0.7916766899206158,
178
+ "eval_loss": 0.9702656269073486,
179
+ "eval_precision_macro": 0.7151431879177634,
180
+ "eval_precision_micro": 0.7916766899206158,
181
+ "eval_recall_macro": 0.7011458309909235,
182
+ "eval_recall_micro": 0.7916766899206158,
183
+ "eval_runtime": 10.9658,
184
+ "eval_samples_per_second": 379.088,
185
+ "eval_steps_per_second": 47.42,
186
+ "step": 4000
187
+ },
188
+ {
189
+ "epoch": 1.0927634774162214,
190
+ "grad_norm": 172.94845581054688,
191
+ "learning_rate": 7.295672280620509e-05,
192
+ "loss": 0.5502,
193
+ "step": 4500
194
+ },
195
+ {
196
+ "epoch": 1.0927634774162214,
197
+ "eval_accuracy": 0.7919172480153958,
198
+ "eval_f1_macro": 0.6957819662499832,
199
+ "eval_f1_micro": 0.7919172480153958,
200
+ "eval_loss": 1.2892016172409058,
201
+ "eval_precision_macro": 0.7464054287468073,
202
+ "eval_precision_micro": 0.7919172480153958,
203
+ "eval_recall_macro": 0.7183926804593861,
204
+ "eval_recall_micro": 0.7919172480153958,
205
+ "eval_runtime": 10.9635,
206
+ "eval_samples_per_second": 379.169,
207
+ "eval_steps_per_second": 47.43,
208
+ "step": 4500
209
+ },
210
+ {
211
+ "epoch": 1.2141816415735793,
212
+ "grad_norm": 203.87509155273438,
213
+ "learning_rate": 7.037435815032454e-05,
214
+ "loss": 0.4406,
215
+ "step": 5000
216
+ },
217
+ {
218
+ "epoch": 1.2141816415735793,
219
+ "eval_accuracy": 0.7570363242723117,
220
+ "eval_f1_macro": 0.6814189298571549,
221
+ "eval_f1_micro": 0.7570363242723117,
222
+ "eval_loss": 1.303400993347168,
223
+ "eval_precision_macro": 0.6973642430073081,
224
+ "eval_precision_micro": 0.7570363242723117,
225
+ "eval_recall_macro": 0.7124908812551407,
226
+ "eval_recall_micro": 0.7570363242723117,
227
+ "eval_runtime": 11.0017,
228
+ "eval_samples_per_second": 377.851,
229
+ "eval_steps_per_second": 47.265,
230
+ "step": 5000
231
+ },
232
+ {
233
+ "epoch": 1.3355998057309373,
234
+ "grad_norm": 0.6460123062133789,
235
+ "learning_rate": 6.74512640603739e-05,
236
+ "loss": 0.519,
237
+ "step": 5500
238
+ },
239
+ {
240
+ "epoch": 1.3355998057309373,
241
+ "eval_accuracy": 0.7827760404137599,
242
+ "eval_f1_macro": 0.7094534682279328,
243
+ "eval_f1_micro": 0.7827760404137599,
244
+ "eval_loss": 1.209078073501587,
245
+ "eval_precision_macro": 0.7201329832289568,
246
+ "eval_precision_micro": 0.7827760404137599,
247
+ "eval_recall_macro": 0.736328566738048,
248
+ "eval_recall_micro": 0.7827760404137599,
249
+ "eval_runtime": 10.9557,
250
+ "eval_samples_per_second": 379.437,
251
+ "eval_steps_per_second": 47.464,
252
+ "step": 5500
253
+ },
254
+ {
255
+ "epoch": 1.4570179698882952,
256
+ "grad_norm": 31.10455894470215,
257
+ "learning_rate": 6.42202308323677e-05,
258
+ "loss": 0.4404,
259
+ "step": 6000
260
+ },
261
+ {
262
+ "epoch": 1.4570179698882952,
263
+ "eval_accuracy": 0.8219870098628819,
264
+ "eval_f1_macro": 0.7542030095306345,
265
+ "eval_f1_micro": 0.8219870098628819,
266
+ "eval_loss": 1.026336908340454,
267
+ "eval_precision_macro": 0.7576623753992426,
268
+ "eval_precision_micro": 0.8219870098628819,
269
+ "eval_recall_macro": 0.7925456800333246,
270
+ "eval_recall_micro": 0.8219870098628819,
271
+ "eval_runtime": 10.9685,
272
+ "eval_samples_per_second": 378.993,
273
+ "eval_steps_per_second": 47.408,
274
+ "step": 6000
275
+ },
276
+ {
277
+ "epoch": 1.5784361340456532,
278
+ "grad_norm": 1.794871211051941,
279
+ "learning_rate": 6.0717503121017445e-05,
280
+ "loss": 0.3789,
281
+ "step": 6500
282
+ },
283
+ {
284
+ "epoch": 1.5784361340456532,
285
+ "eval_accuracy": 0.8542217945633871,
286
+ "eval_f1_macro": 0.7787297552725382,
287
+ "eval_f1_micro": 0.8542217945633871,
288
+ "eval_loss": 0.8210395574569702,
289
+ "eval_precision_macro": 0.8034809592650944,
290
+ "eval_precision_micro": 0.8542217945633871,
291
+ "eval_recall_macro": 0.7731802437378531,
292
+ "eval_recall_micro": 0.8542217945633871,
293
+ "eval_runtime": 10.9547,
294
+ "eval_samples_per_second": 379.473,
295
+ "eval_steps_per_second": 47.468,
296
+ "step": 6500
297
+ },
298
+ {
299
+ "epoch": 1.6998542982030111,
300
+ "grad_norm": 34.32925033569336,
301
+ "learning_rate": 5.69823733592655e-05,
302
+ "loss": 0.3734,
303
+ "step": 7000
304
+ },
305
+ {
306
+ "epoch": 1.6998542982030111,
307
+ "eval_accuracy": 0.7806110175607409,
308
+ "eval_f1_macro": 0.699900993601756,
309
+ "eval_f1_micro": 0.7806110175607409,
310
+ "eval_loss": 1.3878446817398071,
311
+ "eval_precision_macro": 0.7723533425562882,
312
+ "eval_precision_micro": 0.7806110175607409,
313
+ "eval_recall_macro": 0.6948437817490168,
314
+ "eval_recall_micro": 0.7806110175607409,
315
+ "eval_runtime": 10.9677,
316
+ "eval_samples_per_second": 379.023,
317
+ "eval_steps_per_second": 47.412,
318
+ "step": 7000
319
+ },
320
+ {
321
+ "epoch": 1.821272462360369,
322
+ "grad_norm": 0.0333857387304306,
323
+ "learning_rate": 5.305674098885817e-05,
324
+ "loss": 0.3417,
325
+ "step": 7500
326
+ },
327
+ {
328
+ "epoch": 1.821272462360369,
329
+ "eval_accuracy": 0.8414722155400529,
330
+ "eval_f1_macro": 0.752167782578507,
331
+ "eval_f1_micro": 0.8414722155400529,
332
+ "eval_loss": 0.9198834896087646,
333
+ "eval_precision_macro": 0.7597509711251361,
334
+ "eval_precision_micro": 0.8414722155400529,
335
+ "eval_recall_macro": 0.7664744721724374,
336
+ "eval_recall_micro": 0.8414722155400529,
337
+ "eval_runtime": 10.9665,
338
+ "eval_samples_per_second": 379.065,
339
+ "eval_steps_per_second": 47.417,
340
+ "step": 7500
341
+ },
342
+ {
343
+ "epoch": 1.942690626517727,
344
+ "grad_norm": 0.03518730029463768,
345
+ "learning_rate": 4.8984642446361996e-05,
346
+ "loss": 0.342,
347
+ "step": 8000
348
+ },
349
+ {
350
+ "epoch": 1.942690626517727,
351
+ "eval_accuracy": 0.821746451768102,
352
+ "eval_f1_macro": 0.738186135147291,
353
+ "eval_f1_micro": 0.821746451768102,
354
+ "eval_loss": 1.0331408977508545,
355
+ "eval_precision_macro": 0.7592295903512796,
356
+ "eval_precision_micro": 0.821746451768102,
357
+ "eval_recall_macro": 0.7439263957407788,
358
+ "eval_recall_micro": 0.821746451768102,
359
+ "eval_runtime": 11.0024,
360
+ "eval_samples_per_second": 377.826,
361
+ "eval_steps_per_second": 47.262,
362
+ "step": 8000
363
+ },
364
+ {
365
+ "epoch": 2.064108790675085,
366
+ "grad_norm": 0.18279767036437988,
367
+ "learning_rate": 4.481175717708393e-05,
368
+ "loss": 0.2898,
369
+ "step": 8500
370
+ },
371
+ {
372
+ "epoch": 2.064108790675085,
373
+ "eval_accuracy": 0.8203031031994227,
374
+ "eval_f1_macro": 0.7478170717551785,
375
+ "eval_f1_micro": 0.8203031031994227,
376
+ "eval_loss": 1.1277570724487305,
377
+ "eval_precision_macro": 0.7730855406484367,
378
+ "eval_precision_micro": 0.8203031031994227,
379
+ "eval_recall_macro": 0.7543267040014913,
380
+ "eval_recall_micro": 0.8203031031994227,
381
+ "eval_runtime": 10.9448,
382
+ "eval_samples_per_second": 379.815,
383
+ "eval_steps_per_second": 47.511,
384
+ "step": 8500
385
+ },
386
+ {
387
+ "epoch": 2.1855269548324427,
388
+ "grad_norm": 0.01960030198097229,
389
+ "learning_rate": 4.058489521826674e-05,
390
+ "loss": 0.1742,
391
+ "step": 9000
392
+ },
393
+ {
394
+ "epoch": 2.1855269548324427,
395
+ "eval_accuracy": 0.8419533317296127,
396
+ "eval_f1_macro": 0.7694964141590861,
397
+ "eval_f1_micro": 0.8419533317296127,
398
+ "eval_loss": 1.0578076839447021,
399
+ "eval_precision_macro": 0.7655705311822759,
400
+ "eval_precision_micro": 0.8419533317296127,
401
+ "eval_recall_macro": 0.7997867857803433,
402
+ "eval_recall_micro": 0.8419533317296127,
403
+ "eval_runtime": 11.1045,
404
+ "eval_samples_per_second": 374.354,
405
+ "eval_steps_per_second": 46.828,
406
+ "step": 9000
407
+ },
408
+ {
409
+ "epoch": 2.306945118989801,
410
+ "grad_norm": 1.8985679149627686,
411
+ "learning_rate": 3.635147209968037e-05,
412
+ "loss": 0.2277,
413
+ "step": 9500
414
+ },
415
+ {
416
+ "epoch": 2.306945118989801,
417
+ "eval_accuracy": 0.8551840269425066,
418
+ "eval_f1_macro": 0.8010324516227308,
419
+ "eval_f1_micro": 0.8551840269425066,
420
+ "eval_loss": 0.95162034034729,
421
+ "eval_precision_macro": 0.7994379036468637,
422
+ "eval_precision_micro": 0.8551840269425066,
423
+ "eval_recall_macro": 0.8284130356636192,
424
+ "eval_recall_micro": 0.8551840269425066,
425
+ "eval_runtime": 10.9658,
426
+ "eval_samples_per_second": 379.089,
427
+ "eval_steps_per_second": 47.42,
428
+ "step": 9500
429
+ },
430
+ {
431
+ "epoch": 2.4283632831471587,
432
+ "grad_norm": 0.08672552555799484,
433
+ "learning_rate": 3.215897695200002e-05,
434
+ "loss": 0.1459,
435
+ "step": 10000
436
+ },
437
+ {
438
+ "epoch": 2.4283632831471587,
439
+ "eval_accuracy": 0.8580707240798653,
440
+ "eval_f1_macro": 0.7735650259965305,
441
+ "eval_f1_micro": 0.8580707240798653,
442
+ "eval_loss": 0.9313622713088989,
443
+ "eval_precision_macro": 0.8197415932054871,
444
+ "eval_precision_micro": 0.8580707240798653,
445
+ "eval_recall_macro": 0.774173537961469,
446
+ "eval_recall_micro": 0.8580707240798653,
447
+ "eval_runtime": 11.0033,
448
+ "eval_samples_per_second": 377.797,
449
+ "eval_steps_per_second": 47.259,
450
+ "step": 10000
451
+ },
452
+ {
453
+ "epoch": 2.549781447304517,
454
+ "grad_norm": 0.010399931110441685,
455
+ "learning_rate": 2.8062530261954673e-05,
456
+ "loss": 0.1634,
457
+ "step": 10500
458
+ },
459
+ {
460
+ "epoch": 2.549781447304517,
461
+ "eval_accuracy": 0.8443589126774116,
462
+ "eval_f1_macro": 0.7537922358196677,
463
+ "eval_f1_micro": 0.8443589126774116,
464
+ "eval_loss": 1.0135008096694946,
465
+ "eval_precision_macro": 0.8301941849742014,
466
+ "eval_precision_micro": 0.8443589126774116,
467
+ "eval_recall_macro": 0.7457995267519847,
468
+ "eval_recall_micro": 0.8443589126774116,
469
+ "eval_runtime": 11.0399,
470
+ "eval_samples_per_second": 376.542,
471
+ "eval_steps_per_second": 47.102,
472
+ "step": 10500
473
+ },
474
+ {
475
+ "epoch": 2.6711996114618746,
476
+ "grad_norm": 0.012511692009866238,
477
+ "learning_rate": 2.409168137642188e-05,
478
+ "loss": 0.151,
479
+ "step": 11000
480
+ },
481
+ {
482
+ "epoch": 2.6711996114618746,
483
+ "eval_accuracy": 0.8794803945152755,
484
+ "eval_f1_macro": 0.8238485237925146,
485
+ "eval_f1_micro": 0.8794803945152755,
486
+ "eval_loss": 0.798862636089325,
487
+ "eval_precision_macro": 0.8338077165115332,
488
+ "eval_precision_micro": 0.8794803945152755,
489
+ "eval_recall_macro": 0.8296556196318619,
490
+ "eval_recall_micro": 0.8794803945152755,
491
+ "eval_runtime": 11.0936,
492
+ "eval_samples_per_second": 374.72,
493
+ "eval_steps_per_second": 46.874,
494
+ "step": 11000
495
+ },
496
+ {
497
+ "epoch": 2.7926177756192327,
498
+ "grad_norm": 0.5942862033843994,
499
+ "learning_rate": 2.0299286711215096e-05,
500
+ "loss": 0.1627,
501
+ "step": 11500
502
+ },
503
+ {
504
+ "epoch": 2.7926177756192327,
505
+ "eval_accuracy": 0.8833293240317537,
506
+ "eval_f1_macro": 0.8258632320077727,
507
+ "eval_f1_micro": 0.8833293240317537,
508
+ "eval_loss": 0.7369428873062134,
509
+ "eval_precision_macro": 0.8208617314770252,
510
+ "eval_precision_micro": 0.8833293240317537,
511
+ "eval_recall_macro": 0.842352557212921,
512
+ "eval_recall_micro": 0.8833293240317537,
513
+ "eval_runtime": 11.0093,
514
+ "eval_samples_per_second": 377.589,
515
+ "eval_steps_per_second": 47.233,
516
+ "step": 11500
517
+ },
518
+ {
519
+ "epoch": 2.9140359397765905,
520
+ "grad_norm": 0.1483508050441742,
521
+ "learning_rate": 1.672788808669644e-05,
522
+ "loss": 0.1147,
523
+ "step": 12000
524
+ },
525
+ {
526
+ "epoch": 2.9140359397765905,
527
+ "eval_accuracy": 0.8607168631224441,
528
+ "eval_f1_macro": 0.8148434050055327,
529
+ "eval_f1_micro": 0.8607168631224441,
530
+ "eval_loss": 0.9235690236091614,
531
+ "eval_precision_macro": 0.8216220364551388,
532
+ "eval_precision_micro": 0.8607168631224441,
533
+ "eval_recall_macro": 0.8206810147792551,
534
+ "eval_recall_micro": 0.8607168631224441,
535
+ "eval_runtime": 10.9967,
536
+ "eval_samples_per_second": 378.023,
537
+ "eval_steps_per_second": 47.287,
538
+ "step": 12000
539
+ },
540
+ {
541
+ "epoch": 3.0354541039339487,
542
+ "grad_norm": 0.015476622618734837,
543
+ "learning_rate": 1.3417548263242596e-05,
544
+ "loss": 0.1495,
545
+ "step": 12500
546
+ },
547
+ {
548
+ "epoch": 3.0354541039339487,
549
+ "eval_accuracy": 0.8857349049795525,
550
+ "eval_f1_macro": 0.8348811939709606,
551
+ "eval_f1_micro": 0.8857349049795525,
552
+ "eval_loss": 0.7240191102027893,
553
+ "eval_precision_macro": 0.8269436011383359,
554
+ "eval_precision_micro": 0.8857349049795525,
555
+ "eval_recall_macro": 0.8585739727750367,
556
+ "eval_recall_micro": 0.8857349049795525,
557
+ "eval_runtime": 10.9994,
558
+ "eval_samples_per_second": 377.931,
559
+ "eval_steps_per_second": 47.275,
560
+ "step": 12500
561
+ },
562
+ {
563
+ "epoch": 3.1568722680913064,
564
+ "grad_norm": 0.003895299741998315,
565
+ "learning_rate": 1.040540153054102e-05,
566
+ "loss": 0.0428,
567
+ "step": 13000
568
+ },
569
+ {
570
+ "epoch": 3.1568722680913064,
571
+ "eval_accuracy": 0.8886216021169112,
572
+ "eval_f1_macro": 0.8320140900627028,
573
+ "eval_f1_micro": 0.8886216021169112,
574
+ "eval_loss": 0.7417625188827515,
575
+ "eval_precision_macro": 0.8215695976609916,
576
+ "eval_precision_micro": 0.8886216021169112,
577
+ "eval_recall_macro": 0.8562463713090399,
578
+ "eval_recall_micro": 0.8886216021169112,
579
+ "eval_runtime": 10.993,
580
+ "eval_samples_per_second": 378.15,
581
+ "eval_steps_per_second": 47.303,
582
+ "step": 13000
583
+ },
584
+ {
585
+ "epoch": 3.2782904322486646,
586
+ "grad_norm": 0.009999997913837433,
587
+ "learning_rate": 7.725237147495241e-06,
588
+ "loss": 0.0674,
589
+ "step": 13500
590
+ },
591
+ {
592
+ "epoch": 3.2782904322486646,
593
+ "eval_accuracy": 0.863122444070243,
594
+ "eval_f1_macro": 0.8141275248610652,
595
+ "eval_f1_micro": 0.863122444070243,
596
+ "eval_loss": 0.9269203543663025,
597
+ "eval_precision_macro": 0.8155994650555717,
598
+ "eval_precision_micro": 0.863122444070243,
599
+ "eval_recall_macro": 0.831120303176534,
600
+ "eval_recall_micro": 0.863122444070243,
601
+ "eval_runtime": 11.0377,
602
+ "eval_samples_per_second": 376.619,
603
+ "eval_steps_per_second": 47.111,
604
+ "step": 13500
605
+ },
606
+ {
607
+ "epoch": 3.3997085964060223,
608
+ "grad_norm": 0.002102572238072753,
609
+ "learning_rate": 5.411377224960022e-06,
610
+ "loss": 0.0348,
611
+ "step": 14000
612
+ },
613
+ {
614
+ "epoch": 3.3997085964060223,
615
+ "eval_accuracy": 0.8864565792638922,
616
+ "eval_f1_macro": 0.8278883555316573,
617
+ "eval_f1_micro": 0.8864565792638922,
618
+ "eval_loss": 0.7893477082252502,
619
+ "eval_precision_macro": 0.8234196007036506,
620
+ "eval_precision_micro": 0.8864565792638922,
621
+ "eval_recall_macro": 0.8436628954935477,
622
+ "eval_recall_micro": 0.8864565792638922,
623
+ "eval_runtime": 10.991,
624
+ "eval_samples_per_second": 378.217,
625
+ "eval_steps_per_second": 47.311,
626
+ "step": 14000
627
+ },
628
+ {
629
+ "epoch": 3.52112676056338,
630
+ "grad_norm": 0.0026018042117357254,
631
+ "learning_rate": 3.4805125817474373e-06,
632
+ "loss": 0.0429,
633
+ "step": 14500
634
+ },
635
+ {
636
+ "epoch": 3.52112676056338,
637
+ "eval_accuracy": 0.8883810440221314,
638
+ "eval_f1_macro": 0.8359878499067832,
639
+ "eval_f1_micro": 0.8883810440221314,
640
+ "eval_loss": 0.7969309091567993,
641
+ "eval_precision_macro": 0.8351453883280561,
642
+ "eval_precision_micro": 0.8883810440221314,
643
+ "eval_recall_macro": 0.8493998324444691,
644
+ "eval_recall_micro": 0.8883810440221314,
645
+ "eval_runtime": 10.9595,
646
+ "eval_samples_per_second": 379.305,
647
+ "eval_steps_per_second": 47.447,
648
+ "step": 14500
649
+ },
650
+ {
651
+ "epoch": 3.642544924720738,
652
+ "grad_norm": 0.005027813836932182,
653
+ "learning_rate": 1.9619328163448515e-06,
654
+ "loss": 0.0472,
655
+ "step": 15000
656
+ },
657
+ {
658
+ "epoch": 3.642544924720738,
659
+ "eval_accuracy": 0.8871782535482319,
660
+ "eval_f1_macro": 0.8293197008433407,
661
+ "eval_f1_micro": 0.8871782535482319,
662
+ "eval_loss": 0.7746603488922119,
663
+ "eval_precision_macro": 0.8285879613227065,
664
+ "eval_precision_micro": 0.8871782535482319,
665
+ "eval_recall_macro": 0.843758966912644,
666
+ "eval_recall_micro": 0.8871782535482319,
667
+ "eval_runtime": 10.9555,
668
+ "eval_samples_per_second": 379.444,
669
+ "eval_steps_per_second": 47.465,
670
+ "step": 15000
671
+ },
672
+ {
673
+ "epoch": 3.7639630888780964,
674
+ "grad_norm": 0.001474579912610352,
675
+ "learning_rate": 8.665920662387894e-07,
676
+ "loss": 0.0654,
677
+ "step": 15500
678
+ },
679
+ {
680
+ "epoch": 3.7639630888780964,
681
+ "eval_accuracy": 0.8878999278325715,
682
+ "eval_f1_macro": 0.8333706258627294,
683
+ "eval_f1_micro": 0.8878999278325715,
684
+ "eval_loss": 0.7646775841712952,
685
+ "eval_precision_macro": 0.8323851081178661,
686
+ "eval_precision_micro": 0.8878999278325715,
687
+ "eval_recall_macro": 0.8465412634330337,
688
+ "eval_recall_micro": 0.8878999278325715,
689
+ "eval_runtime": 11.0797,
690
+ "eval_samples_per_second": 375.191,
691
+ "eval_steps_per_second": 46.933,
692
+ "step": 15500
693
+ },
694
+ {
695
+ "epoch": 3.885381253035454,
696
+ "grad_norm": 0.02036176808178425,
697
+ "learning_rate": 2.1023685362179913e-07,
698
+ "loss": 0.0519,
699
+ "step": 16000
700
+ },
701
+ {
702
+ "epoch": 3.885381253035454,
703
+ "eval_accuracy": 0.8910271830647102,
704
+ "eval_f1_macro": 0.8388668685961359,
705
+ "eval_f1_micro": 0.8910271830647102,
706
+ "eval_loss": 0.7371587753295898,
707
+ "eval_precision_macro": 0.8351964171775984,
708
+ "eval_precision_micro": 0.8910271830647102,
709
+ "eval_recall_macro": 0.8528710223600782,
710
+ "eval_recall_micro": 0.8910271830647102,
711
+ "eval_runtime": 10.9604,
712
+ "eval_samples_per_second": 379.273,
713
+ "eval_steps_per_second": 47.443,
714
+ "step": 16000
715
+ }
716
+ ],
717
+ "logging_steps": 500,
718
+ "max_steps": 16472,
719
+ "num_input_tokens_seen": 0,
720
+ "num_train_epochs": 4,
721
+ "save_steps": 500,
722
+ "stateful_callbacks": {
723
+ "TrainerControl": {
724
+ "args": {
725
+ "should_epoch_stop": false,
726
+ "should_evaluate": false,
727
+ "should_log": false,
728
+ "should_save": true,
729
+ "should_training_stop": true
730
+ },
731
+ "attributes": {}
732
+ }
733
+ },
734
+ "total_flos": 3.4790744808566784e+16,
735
+ "train_batch_size": 8,
736
+ "trial_name": null,
737
+ "trial_params": null
738
+ }
checkpoint-16472/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:733beefefbbbe74f348894313550142320fa88d841d14225798e6321192444dd
3
+ size 5713
checkpoint-16472/vocab.txt ADDED
The diff for this file is too large to render. See raw diff