Hugging Face's logo

MuhammadHelmy
/
xlm-roberta-base-arabic-AuthId

Safetensors
xlm-roberta
Model card Files
xet
Community
MuhammadHelmy commited on
Commit
e9cbbb0
·
verified ·
1 Parent(s): 137563d

Upload folder using huggingface_hub

Browse files
Files changed (30) hide show
  1. .gitattributes +3 -0
  2. checkpoint-6500/config.json +77 -0
  3. checkpoint-6500/model.safetensors +3 -0
  4. checkpoint-6500/optimizer.pt +3 -0
  5. checkpoint-6500/rng_state.pth +3 -0
  6. checkpoint-6500/scheduler.pt +3 -0
  7. checkpoint-6500/sentencepiece.bpe.model +3 -0
  8. checkpoint-6500/special_tokens_map.json +51 -0
  9. checkpoint-6500/tokenizer.json +3 -0
  10. checkpoint-6500/tokenizer_config.json +65 -0
  11. checkpoint-6500/trainer_state.json +281 -0
  12. checkpoint-6500/training_args.bin +3 -0
  13. checkpoint-8236/config.json +77 -0
  14. checkpoint-8236/model.safetensors +3 -0
  15. checkpoint-8236/optimizer.pt +3 -0
  16. checkpoint-8236/rng_state.pth +3 -0
  17. checkpoint-8236/scheduler.pt +3 -0
  18. checkpoint-8236/sentencepiece.bpe.model +3 -0
  19. checkpoint-8236/special_tokens_map.json +51 -0
  20. checkpoint-8236/tokenizer.json +3 -0
  21. checkpoint-8236/tokenizer_config.json +65 -0
  22. checkpoint-8236/trainer_state.json +338 -0
  23. checkpoint-8236/training_args.bin +3 -0
  24. config.json +77 -0
  25. model.safetensors +3 -0
  26. sentencepiece.bpe.model +3 -0
  27. special_tokens_map.json +51 -0
  28. tokenizer.json +3 -0
  29. tokenizer_config.json +65 -0
  30. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-6500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-8236/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-6500/config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_10": 10,
42
+ "LABEL_11": 11,
43
+ "LABEL_12": 12,
44
+ "LABEL_13": 13,
45
+ "LABEL_14": 14,
46
+ "LABEL_15": 15,
47
+ "LABEL_16": 16,
48
+ "LABEL_17": 17,
49
+ "LABEL_18": 18,
50
+ "LABEL_19": 19,
51
+ "LABEL_2": 2,
52
+ "LABEL_20": 20,
53
+ "LABEL_3": 3,
54
+ "LABEL_4": 4,
55
+ "LABEL_5": 5,
56
+ "LABEL_6": 6,
57
+ "LABEL_7": 7,
58
+ "LABEL_8": 8,
59
+ "LABEL_9": 9
60
+ },
61
+ "language": "english",
62
+ "layer_norm_eps": 1e-05,
63
+ "max_position_embeddings": 514,
64
+ "model_type": "xlm-roberta",
65
+ "name": "XLMRoberta",
66
+ "num_attention_heads": 12,
67
+ "num_hidden_layers": 12,
68
+ "output_past": true,
69
+ "pad_token_id": 1,
70
+ "position_embedding_type": "absolute",
71
+ "problem_type": "single_label_classification",
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.52.4",
74
+ "type_vocab_size": 1,
75
+ "use_cache": true,
76
+ "vocab_size": 250002
77
+ }
checkpoint-6500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5683f1bac6b1122975d151772fc9888b1e51026a4bd2b8e3e13b08777cf114ee
3
+ size 1112263452
checkpoint-6500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e48e88bc7e1fd86c15ea5959e37495e53777b6226a73e062fed58822f5261f31
3
+ size 2224646458
checkpoint-6500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1546bc0dce6c7f36842d48a1750e016838baa129df3c5226aa523d34f13d2f8
3
+ size 14244
checkpoint-6500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0002367613c637be631b8420bceba98eb74d55ca05c357a861220029511e7a88
3
+ size 1064
checkpoint-6500/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-6500/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-6500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc419f52a289472c7bc97f403dea966e9eaa4ffd74b547ddfec9f34843877e4
3
+ size 17083065
checkpoint-6500/tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "do_lower_case": false,
48
+ "eos_token": "</s>",
49
+ "extra_special_tokens": {},
50
+ "full_tokenizer_file": null,
51
+ "mask_token": "<mask>",
52
+ "max_length": 256,
53
+ "model_max_length": 512,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "<pad>",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
+ "sep_token": "</s>",
59
+ "sp_model_kwargs": {},
60
+ "stride": 128,
61
+ "tokenizer_class": "XLMRobertaTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "only_second",
64
+ "unk_token": "<unk>"
65
+ }
checkpoint-6500/trainer_state.json ADDED
@@ -0,0 +1,281 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 6500,
3
+ "best_metric": 0.8331692828985621,
4
+ "best_model_checkpoint": "./xlm-roberta-base-arabic-AuthId/checkpoint-6500",
5
+ "epoch": 3.1568722680913064,
6
+ "eval_steps": 500,
7
+ "global_step": 6500,
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": 8.986019134521484,
15
+ "learning_rate": 4.8446601941747576e-05,
16
+ "loss": 2.5137,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.24283632831471588,
21
+ "eval_accuracy": 0.45441424103921096,
22
+ "eval_f1_macro": 0.3407124373053575,
23
+ "eval_loss": 1.79319429397583,
24
+ "eval_precision_macro": 0.41829450325464324,
25
+ "eval_recall_macro": 0.38754753521002216,
26
+ "eval_runtime": 90.6145,
27
+ "eval_samples_per_second": 45.876,
28
+ "eval_steps_per_second": 2.869,
29
+ "step": 500
30
+ },
31
+ {
32
+ "epoch": 0.48567265662943176,
33
+ "grad_norm": 15.8992338180542,
34
+ "learning_rate": 7.989001438410175e-05,
35
+ "loss": 1.4354,
36
+ "step": 1000
37
+ },
38
+ {
39
+ "epoch": 0.48567265662943176,
40
+ "eval_accuracy": 0.5316333894635554,
41
+ "eval_f1_macro": 0.41842554486229444,
42
+ "eval_loss": 1.637890338897705,
43
+ "eval_precision_macro": 0.4373908716894125,
44
+ "eval_recall_macro": 0.4627672589255464,
45
+ "eval_runtime": 90.6363,
46
+ "eval_samples_per_second": 45.865,
47
+ "eval_steps_per_second": 2.869,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 0.7285089849441476,
52
+ "grad_norm": 27.575876235961914,
53
+ "learning_rate": 7.837406915300635e-05,
54
+ "loss": 0.9864,
55
+ "step": 1500
56
+ },
57
+ {
58
+ "epoch": 0.7285089849441476,
59
+ "eval_accuracy": 0.6401250902092855,
60
+ "eval_f1_macro": 0.5279363573976125,
61
+ "eval_loss": 1.3957277536392212,
62
+ "eval_precision_macro": 0.5967395793608964,
63
+ "eval_recall_macro": 0.5512997179736142,
64
+ "eval_runtime": 93.5089,
65
+ "eval_samples_per_second": 44.456,
66
+ "eval_steps_per_second": 2.78,
67
+ "step": 1500
68
+ },
69
+ {
70
+ "epoch": 0.9713453132588635,
71
+ "grad_norm": 32.76620101928711,
72
+ "learning_rate": 7.514108265155405e-05,
73
+ "loss": 0.7963,
74
+ "step": 2000
75
+ },
76
+ {
77
+ "epoch": 0.9713453132588635,
78
+ "eval_accuracy": 0.6418089968727447,
79
+ "eval_f1_macro": 0.5605457346360582,
80
+ "eval_loss": 1.2943669557571411,
81
+ "eval_precision_macro": 0.6000129481226912,
82
+ "eval_recall_macro": 0.6016057761339161,
83
+ "eval_runtime": 93.8364,
84
+ "eval_samples_per_second": 44.3,
85
+ "eval_steps_per_second": 2.771,
86
+ "step": 2000
87
+ },
88
+ {
89
+ "epoch": 1.2141816415735793,
90
+ "grad_norm": 11.139548301696777,
91
+ "learning_rate": 7.033571431701654e-05,
92
+ "loss": 0.5633,
93
+ "step": 2500
94
+ },
95
+ {
96
+ "epoch": 1.2141816415735793,
97
+ "eval_accuracy": 0.6971373586721193,
98
+ "eval_f1_macro": 0.639747487019458,
99
+ "eval_loss": 1.1428158283233643,
100
+ "eval_precision_macro": 0.6645979393585295,
101
+ "eval_recall_macro": 0.6641315729499758,
102
+ "eval_runtime": 93.4249,
103
+ "eval_samples_per_second": 44.496,
104
+ "eval_steps_per_second": 2.783,
105
+ "step": 2500
106
+ },
107
+ {
108
+ "epoch": 1.4570179698882952,
109
+ "grad_norm": 21.638471603393555,
110
+ "learning_rate": 6.417297954733794e-05,
111
+ "loss": 0.4873,
112
+ "step": 3000
113
+ },
114
+ {
115
+ "epoch": 1.4570179698882952,
116
+ "eval_accuracy": 0.7190281452970892,
117
+ "eval_f1_macro": 0.6808895651910684,
118
+ "eval_loss": 1.1293725967407227,
119
+ "eval_precision_macro": 0.7195977672422045,
120
+ "eval_recall_macro": 0.6881777255438714,
121
+ "eval_runtime": 93.7403,
122
+ "eval_samples_per_second": 44.346,
123
+ "eval_steps_per_second": 2.774,
124
+ "step": 3000
125
+ },
126
+ {
127
+ "epoch": 1.6998542982030111,
128
+ "grad_norm": 6.6594462394714355,
129
+ "learning_rate": 5.692862887331573e-05,
130
+ "loss": 0.407,
131
+ "step": 3500
132
+ },
133
+ {
134
+ "epoch": 1.6998542982030111,
135
+ "eval_accuracy": 0.7712292518643252,
136
+ "eval_f1_macro": 0.708039555200591,
137
+ "eval_loss": 0.9486013054847717,
138
+ "eval_precision_macro": 0.7450683804103814,
139
+ "eval_recall_macro": 0.7298859494848938,
140
+ "eval_runtime": 90.5152,
141
+ "eval_samples_per_second": 45.926,
142
+ "eval_steps_per_second": 2.872,
143
+ "step": 3500
144
+ },
145
+ {
146
+ "epoch": 1.942690626517727,
147
+ "grad_norm": 1.6757619380950928,
148
+ "learning_rate": 4.892680954747708e-05,
149
+ "loss": 0.345,
150
+ "step": 4000
151
+ },
152
+ {
153
+ "epoch": 1.942690626517727,
154
+ "eval_accuracy": 0.7996151070483521,
155
+ "eval_f1_macro": 0.7418253710648876,
156
+ "eval_loss": 0.8268765211105347,
157
+ "eval_precision_macro": 0.7454305862830231,
158
+ "eval_recall_macro": 0.7679024585769894,
159
+ "eval_runtime": 93.8625,
160
+ "eval_samples_per_second": 44.288,
161
+ "eval_steps_per_second": 2.77,
162
+ "step": 4000
163
+ },
164
+ {
165
+ "epoch": 2.1855269548324427,
166
+ "grad_norm": 0.2650994062423706,
167
+ "learning_rate": 4.052556162978074e-05,
168
+ "loss": 0.245,
169
+ "step": 4500
170
+ },
171
+ {
172
+ "epoch": 2.1855269548324427,
173
+ "eval_accuracy": 0.8467644936252104,
174
+ "eval_f1_macro": 0.7932738890751645,
175
+ "eval_loss": 0.6939923763275146,
176
+ "eval_precision_macro": 0.7951455984390196,
177
+ "eval_recall_macro": 0.8095792155211485,
178
+ "eval_runtime": 93.5208,
179
+ "eval_samples_per_second": 44.45,
180
+ "eval_steps_per_second": 2.78,
181
+ "step": 4500
182
+ },
183
+ {
184
+ "epoch": 2.4283632831471587,
185
+ "grad_norm": 17.687816619873047,
186
+ "learning_rate": 3.2100797545350794e-05,
187
+ "loss": 0.1974,
188
+ "step": 5000
189
+ },
190
+ {
191
+ "epoch": 2.4283632831471587,
192
+ "eval_accuracy": 0.8513350974260284,
193
+ "eval_f1_macro": 0.7904651787941427,
194
+ "eval_loss": 0.7257494330406189,
195
+ "eval_precision_macro": 0.7893882754186418,
196
+ "eval_recall_macro": 0.8202838664722221,
197
+ "eval_runtime": 93.4617,
198
+ "eval_samples_per_second": 44.478,
199
+ "eval_steps_per_second": 2.782,
200
+ "step": 5000
201
+ },
202
+ {
203
+ "epoch": 2.6711996114618746,
204
+ "grad_norm": 16.58666229248047,
205
+ "learning_rate": 2.402948194623674e-05,
206
+ "loss": 0.1912,
207
+ "step": 5500
208
+ },
209
+ {
210
+ "epoch": 2.6711996114618746,
211
+ "eval_accuracy": 0.8443589126774116,
212
+ "eval_f1_macro": 0.7766386003848027,
213
+ "eval_loss": 0.815396785736084,
214
+ "eval_precision_macro": 0.7931363496424888,
215
+ "eval_recall_macro": 0.7977471811181303,
216
+ "eval_runtime": 93.456,
217
+ "eval_samples_per_second": 44.481,
218
+ "eval_steps_per_second": 2.782,
219
+ "step": 5500
220
+ },
221
+ {
222
+ "epoch": 2.9140359397765905,
223
+ "grad_norm": 0.10645630210638046,
224
+ "learning_rate": 1.667276449145691e-05,
225
+ "loss": 0.1398,
226
+ "step": 6000
227
+ },
228
+ {
229
+ "epoch": 2.9140359397765905,
230
+ "eval_accuracy": 0.8720230935770988,
231
+ "eval_f1_macro": 0.8112907838723983,
232
+ "eval_loss": 0.6746448278427124,
233
+ "eval_precision_macro": 0.8095950706198851,
234
+ "eval_recall_macro": 0.8248032200653025,
235
+ "eval_runtime": 90.9246,
236
+ "eval_samples_per_second": 45.719,
237
+ "eval_steps_per_second": 2.86,
238
+ "step": 6000
239
+ },
240
+ {
241
+ "epoch": 3.1568722680913064,
242
+ "grad_norm": 0.05953911691904068,
243
+ "learning_rate": 1.035982026624521e-05,
244
+ "loss": 0.0841,
245
+ "step": 6500
246
+ },
247
+ {
248
+ "epoch": 3.1568722680913064,
249
+ "eval_accuracy": 0.8787587202309358,
250
+ "eval_f1_macro": 0.8331692828985621,
251
+ "eval_loss": 0.6558229923248291,
252
+ "eval_precision_macro": 0.837208474561673,
253
+ "eval_recall_macro": 0.8359818272777001,
254
+ "eval_runtime": 93.623,
255
+ "eval_samples_per_second": 44.401,
256
+ "eval_steps_per_second": 2.777,
257
+ "step": 6500
258
+ }
259
+ ],
260
+ "logging_steps": 500,
261
+ "max_steps": 8236,
262
+ "num_input_tokens_seen": 0,
263
+ "num_train_epochs": 4,
264
+ "save_steps": 500,
265
+ "stateful_callbacks": {
266
+ "TrainerControl": {
267
+ "args": {
268
+ "should_epoch_stop": false,
269
+ "should_evaluate": false,
270
+ "should_log": false,
271
+ "should_save": true,
272
+ "should_training_stop": false
273
+ },
274
+ "attributes": {}
275
+ }
276
+ },
277
+ "total_flos": 2.736584939314483e+16,
278
+ "train_batch_size": 16,
279
+ "trial_name": null,
280
+ "trial_params": null
281
+ }
checkpoint-6500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a265a0de87aae5eb11cd3efc056bf622830d469cfcaa1ec8aafda9ceaeeeb539
3
+ size 5304
checkpoint-8236/config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_10": 10,
42
+ "LABEL_11": 11,
43
+ "LABEL_12": 12,
44
+ "LABEL_13": 13,
45
+ "LABEL_14": 14,
46
+ "LABEL_15": 15,
47
+ "LABEL_16": 16,
48
+ "LABEL_17": 17,
49
+ "LABEL_18": 18,
50
+ "LABEL_19": 19,
51
+ "LABEL_2": 2,
52
+ "LABEL_20": 20,
53
+ "LABEL_3": 3,
54
+ "LABEL_4": 4,
55
+ "LABEL_5": 5,
56
+ "LABEL_6": 6,
57
+ "LABEL_7": 7,
58
+ "LABEL_8": 8,
59
+ "LABEL_9": 9
60
+ },
61
+ "language": "english",
62
+ "layer_norm_eps": 1e-05,
63
+ "max_position_embeddings": 514,
64
+ "model_type": "xlm-roberta",
65
+ "name": "XLMRoberta",
66
+ "num_attention_heads": 12,
67
+ "num_hidden_layers": 12,
68
+ "output_past": true,
69
+ "pad_token_id": 1,
70
+ "position_embedding_type": "absolute",
71
+ "problem_type": "single_label_classification",
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.52.4",
74
+ "type_vocab_size": 1,
75
+ "use_cache": true,
76
+ "vocab_size": 250002
77
+ }
checkpoint-8236/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ed28e45f1ad1324f6e1a9f2f49b4ea22b5af636c445892a2c9e72219ec6102
3
+ size 1112263452
checkpoint-8236/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05f528db87fa79f89d1d2027c0895f8ee77d4e056f65c85eaa94555384870642
3
+ size 2224646458
checkpoint-8236/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4736edaa5baa659a6e16505ce8e97185eb074c9bf73c9d77cab170e8acda83
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/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-8236/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-8236/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc419f52a289472c7bc97f403dea966e9eaa4ffd74b547ddfec9f34843877e4
3
+ size 17083065
checkpoint-8236/tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "do_lower_case": false,
48
+ "eos_token": "</s>",
49
+ "extra_special_tokens": {},
50
+ "full_tokenizer_file": null,
51
+ "mask_token": "<mask>",
52
+ "max_length": 256,
53
+ "model_max_length": 512,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "<pad>",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
+ "sep_token": "</s>",
59
+ "sp_model_kwargs": {},
60
+ "stride": 128,
61
+ "tokenizer_class": "XLMRobertaTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "only_second",
64
+ "unk_token": "<unk>"
65
+ }
checkpoint-8236/trainer_state.json ADDED
@@ -0,0 +1,338 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 6500,
3
+ "best_metric": 0.8331692828985621,
4
+ "best_model_checkpoint": "./xlm-roberta-base-arabic-AuthId/checkpoint-6500",
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": 8.986019134521484,
15
+ "learning_rate": 4.8446601941747576e-05,
16
+ "loss": 2.5137,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.24283632831471588,
21
+ "eval_accuracy": 0.45441424103921096,
22
+ "eval_f1_macro": 0.3407124373053575,
23
+ "eval_loss": 1.79319429397583,
24
+ "eval_precision_macro": 0.41829450325464324,
25
+ "eval_recall_macro": 0.38754753521002216,
26
+ "eval_runtime": 90.6145,
27
+ "eval_samples_per_second": 45.876,
28
+ "eval_steps_per_second": 2.869,
29
+ "step": 500
30
+ },
31
+ {
32
+ "epoch": 0.48567265662943176,
33
+ "grad_norm": 15.8992338180542,
34
+ "learning_rate": 7.989001438410175e-05,
35
+ "loss": 1.4354,
36
+ "step": 1000
37
+ },
38
+ {
39
+ "epoch": 0.48567265662943176,
40
+ "eval_accuracy": 0.5316333894635554,
41
+ "eval_f1_macro": 0.41842554486229444,
42
+ "eval_loss": 1.637890338897705,
43
+ "eval_precision_macro": 0.4373908716894125,
44
+ "eval_recall_macro": 0.4627672589255464,
45
+ "eval_runtime": 90.6363,
46
+ "eval_samples_per_second": 45.865,
47
+ "eval_steps_per_second": 2.869,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 0.7285089849441476,
52
+ "grad_norm": 27.575876235961914,
53
+ "learning_rate": 7.837406915300635e-05,
54
+ "loss": 0.9864,
55
+ "step": 1500
56
+ },
57
+ {
58
+ "epoch": 0.7285089849441476,
59
+ "eval_accuracy": 0.6401250902092855,
60
+ "eval_f1_macro": 0.5279363573976125,
61
+ "eval_loss": 1.3957277536392212,
62
+ "eval_precision_macro": 0.5967395793608964,
63
+ "eval_recall_macro": 0.5512997179736142,
64
+ "eval_runtime": 93.5089,
65
+ "eval_samples_per_second": 44.456,
66
+ "eval_steps_per_second": 2.78,
67
+ "step": 1500
68
+ },
69
+ {
70
+ "epoch": 0.9713453132588635,
71
+ "grad_norm": 32.76620101928711,
72
+ "learning_rate": 7.514108265155405e-05,
73
+ "loss": 0.7963,
74
+ "step": 2000
75
+ },
76
+ {
77
+ "epoch": 0.9713453132588635,
78
+ "eval_accuracy": 0.6418089968727447,
79
+ "eval_f1_macro": 0.5605457346360582,
80
+ "eval_loss": 1.2943669557571411,
81
+ "eval_precision_macro": 0.6000129481226912,
82
+ "eval_recall_macro": 0.6016057761339161,
83
+ "eval_runtime": 93.8364,
84
+ "eval_samples_per_second": 44.3,
85
+ "eval_steps_per_second": 2.771,
86
+ "step": 2000
87
+ },
88
+ {
89
+ "epoch": 1.2141816415735793,
90
+ "grad_norm": 11.139548301696777,
91
+ "learning_rate": 7.033571431701654e-05,
92
+ "loss": 0.5633,
93
+ "step": 2500
94
+ },
95
+ {
96
+ "epoch": 1.2141816415735793,
97
+ "eval_accuracy": 0.6971373586721193,
98
+ "eval_f1_macro": 0.639747487019458,
99
+ "eval_loss": 1.1428158283233643,
100
+ "eval_precision_macro": 0.6645979393585295,
101
+ "eval_recall_macro": 0.6641315729499758,
102
+ "eval_runtime": 93.4249,
103
+ "eval_samples_per_second": 44.496,
104
+ "eval_steps_per_second": 2.783,
105
+ "step": 2500
106
+ },
107
+ {
108
+ "epoch": 1.4570179698882952,
109
+ "grad_norm": 21.638471603393555,
110
+ "learning_rate": 6.417297954733794e-05,
111
+ "loss": 0.4873,
112
+ "step": 3000
113
+ },
114
+ {
115
+ "epoch": 1.4570179698882952,
116
+ "eval_accuracy": 0.7190281452970892,
117
+ "eval_f1_macro": 0.6808895651910684,
118
+ "eval_loss": 1.1293725967407227,
119
+ "eval_precision_macro": 0.7195977672422045,
120
+ "eval_recall_macro": 0.6881777255438714,
121
+ "eval_runtime": 93.7403,
122
+ "eval_samples_per_second": 44.346,
123
+ "eval_steps_per_second": 2.774,
124
+ "step": 3000
125
+ },
126
+ {
127
+ "epoch": 1.6998542982030111,
128
+ "grad_norm": 6.6594462394714355,
129
+ "learning_rate": 5.692862887331573e-05,
130
+ "loss": 0.407,
131
+ "step": 3500
132
+ },
133
+ {
134
+ "epoch": 1.6998542982030111,
135
+ "eval_accuracy": 0.7712292518643252,
136
+ "eval_f1_macro": 0.708039555200591,
137
+ "eval_loss": 0.9486013054847717,
138
+ "eval_precision_macro": 0.7450683804103814,
139
+ "eval_recall_macro": 0.7298859494848938,
140
+ "eval_runtime": 90.5152,
141
+ "eval_samples_per_second": 45.926,
142
+ "eval_steps_per_second": 2.872,
143
+ "step": 3500
144
+ },
145
+ {
146
+ "epoch": 1.942690626517727,
147
+ "grad_norm": 1.6757619380950928,
148
+ "learning_rate": 4.892680954747708e-05,
149
+ "loss": 0.345,
150
+ "step": 4000
151
+ },
152
+ {
153
+ "epoch": 1.942690626517727,
154
+ "eval_accuracy": 0.7996151070483521,
155
+ "eval_f1_macro": 0.7418253710648876,
156
+ "eval_loss": 0.8268765211105347,
157
+ "eval_precision_macro": 0.7454305862830231,
158
+ "eval_recall_macro": 0.7679024585769894,
159
+ "eval_runtime": 93.8625,
160
+ "eval_samples_per_second": 44.288,
161
+ "eval_steps_per_second": 2.77,
162
+ "step": 4000
163
+ },
164
+ {
165
+ "epoch": 2.1855269548324427,
166
+ "grad_norm": 0.2650994062423706,
167
+ "learning_rate": 4.052556162978074e-05,
168
+ "loss": 0.245,
169
+ "step": 4500
170
+ },
171
+ {
172
+ "epoch": 2.1855269548324427,
173
+ "eval_accuracy": 0.8467644936252104,
174
+ "eval_f1_macro": 0.7932738890751645,
175
+ "eval_loss": 0.6939923763275146,
176
+ "eval_precision_macro": 0.7951455984390196,
177
+ "eval_recall_macro": 0.8095792155211485,
178
+ "eval_runtime": 93.5208,
179
+ "eval_samples_per_second": 44.45,
180
+ "eval_steps_per_second": 2.78,
181
+ "step": 4500
182
+ },
183
+ {
184
+ "epoch": 2.4283632831471587,
185
+ "grad_norm": 17.687816619873047,
186
+ "learning_rate": 3.2100797545350794e-05,
187
+ "loss": 0.1974,
188
+ "step": 5000
189
+ },
190
+ {
191
+ "epoch": 2.4283632831471587,
192
+ "eval_accuracy": 0.8513350974260284,
193
+ "eval_f1_macro": 0.7904651787941427,
194
+ "eval_loss": 0.7257494330406189,
195
+ "eval_precision_macro": 0.7893882754186418,
196
+ "eval_recall_macro": 0.8202838664722221,
197
+ "eval_runtime": 93.4617,
198
+ "eval_samples_per_second": 44.478,
199
+ "eval_steps_per_second": 2.782,
200
+ "step": 5000
201
+ },
202
+ {
203
+ "epoch": 2.6711996114618746,
204
+ "grad_norm": 16.58666229248047,
205
+ "learning_rate": 2.402948194623674e-05,
206
+ "loss": 0.1912,
207
+ "step": 5500
208
+ },
209
+ {
210
+ "epoch": 2.6711996114618746,
211
+ "eval_accuracy": 0.8443589126774116,
212
+ "eval_f1_macro": 0.7766386003848027,
213
+ "eval_loss": 0.815396785736084,
214
+ "eval_precision_macro": 0.7931363496424888,
215
+ "eval_recall_macro": 0.7977471811181303,
216
+ "eval_runtime": 93.456,
217
+ "eval_samples_per_second": 44.481,
218
+ "eval_steps_per_second": 2.782,
219
+ "step": 5500
220
+ },
221
+ {
222
+ "epoch": 2.9140359397765905,
223
+ "grad_norm": 0.10645630210638046,
224
+ "learning_rate": 1.667276449145691e-05,
225
+ "loss": 0.1398,
226
+ "step": 6000
227
+ },
228
+ {
229
+ "epoch": 2.9140359397765905,
230
+ "eval_accuracy": 0.8720230935770988,
231
+ "eval_f1_macro": 0.8112907838723983,
232
+ "eval_loss": 0.6746448278427124,
233
+ "eval_precision_macro": 0.8095950706198851,
234
+ "eval_recall_macro": 0.8248032200653025,
235
+ "eval_runtime": 90.9246,
236
+ "eval_samples_per_second": 45.719,
237
+ "eval_steps_per_second": 2.86,
238
+ "step": 6000
239
+ },
240
+ {
241
+ "epoch": 3.1568722680913064,
242
+ "grad_norm": 0.05953911691904068,
243
+ "learning_rate": 1.035982026624521e-05,
244
+ "loss": 0.0841,
245
+ "step": 6500
246
+ },
247
+ {
248
+ "epoch": 3.1568722680913064,
249
+ "eval_accuracy": 0.8787587202309358,
250
+ "eval_f1_macro": 0.8331692828985621,
251
+ "eval_loss": 0.6558229923248291,
252
+ "eval_precision_macro": 0.837208474561673,
253
+ "eval_recall_macro": 0.8359818272777001,
254
+ "eval_runtime": 93.623,
255
+ "eval_samples_per_second": 44.401,
256
+ "eval_steps_per_second": 2.777,
257
+ "step": 6500
258
+ },
259
+ {
260
+ "epoch": 3.3997085964060223,
261
+ "grad_norm": 0.02120724879205227,
262
+ "learning_rate": 5.373120898224163e-06,
263
+ "loss": 0.0556,
264
+ "step": 7000
265
+ },
266
+ {
267
+ "epoch": 3.3997085964060223,
268
+ "eval_accuracy": 0.8770748135674765,
269
+ "eval_f1_macro": 0.8228927631345867,
270
+ "eval_loss": 0.6992373466491699,
271
+ "eval_precision_macro": 0.8204504130603765,
272
+ "eval_recall_macro": 0.8332023921988017,
273
+ "eval_runtime": 93.7107,
274
+ "eval_samples_per_second": 44.36,
275
+ "eval_steps_per_second": 2.774,
276
+ "step": 7000
277
+ },
278
+ {
279
+ "epoch": 3.642544924720738,
280
+ "grad_norm": 0.03803861513733864,
281
+ "learning_rate": 1.935795411934156e-06,
282
+ "loss": 0.0609,
283
+ "step": 7500
284
+ },
285
+ {
286
+ "epoch": 3.642544924720738,
287
+ "eval_accuracy": 0.8818859754630743,
288
+ "eval_f1_macro": 0.8258309026136927,
289
+ "eval_loss": 0.6909679770469666,
290
+ "eval_precision_macro": 0.8230008720397977,
291
+ "eval_recall_macro": 0.8384688723183684,
292
+ "eval_runtime": 93.4555,
293
+ "eval_samples_per_second": 44.481,
294
+ "eval_steps_per_second": 2.782,
295
+ "step": 7500
296
+ },
297
+ {
298
+ "epoch": 3.885381253035454,
299
+ "grad_norm": 0.28797557950019836,
300
+ "learning_rate": 2.0164635815698608e-07,
301
+ "loss": 0.0391,
302
+ "step": 8000
303
+ },
304
+ {
305
+ "epoch": 3.885381253035454,
306
+ "eval_accuracy": 0.8814048592735145,
307
+ "eval_f1_macro": 0.8272327688198191,
308
+ "eval_loss": 0.6654815077781677,
309
+ "eval_precision_macro": 0.8196373057336056,
310
+ "eval_recall_macro": 0.8410357781269153,
311
+ "eval_runtime": 93.7631,
312
+ "eval_samples_per_second": 44.335,
313
+ "eval_steps_per_second": 2.773,
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": 3.467447932454093e+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:a265a0de87aae5eb11cd3efc056bf622830d469cfcaa1ec8aafda9ceaeeeb539
3
+ size 5304
config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_10": 10,
42
+ "LABEL_11": 11,
43
+ "LABEL_12": 12,
44
+ "LABEL_13": 13,
45
+ "LABEL_14": 14,
46
+ "LABEL_15": 15,
47
+ "LABEL_16": 16,
48
+ "LABEL_17": 17,
49
+ "LABEL_18": 18,
50
+ "LABEL_19": 19,
51
+ "LABEL_2": 2,
52
+ "LABEL_20": 20,
53
+ "LABEL_3": 3,
54
+ "LABEL_4": 4,
55
+ "LABEL_5": 5,
56
+ "LABEL_6": 6,
57
+ "LABEL_7": 7,
58
+ "LABEL_8": 8,
59
+ "LABEL_9": 9
60
+ },
61
+ "language": "english",
62
+ "layer_norm_eps": 1e-05,
63
+ "max_position_embeddings": 514,
64
+ "model_type": "xlm-roberta",
65
+ "name": "XLMRoberta",
66
+ "num_attention_heads": 12,
67
+ "num_hidden_layers": 12,
68
+ "output_past": true,
69
+ "pad_token_id": 1,
70
+ "position_embedding_type": "absolute",
71
+ "problem_type": "single_label_classification",
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.52.4",
74
+ "type_vocab_size": 1,
75
+ "use_cache": true,
76
+ "vocab_size": 250002
77
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5683f1bac6b1122975d151772fc9888b1e51026a4bd2b8e3e13b08777cf114ee
3
+ size 1112263452
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc419f52a289472c7bc97f403dea966e9eaa4ffd74b547ddfec9f34843877e4
3
+ size 17083065
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "do_lower_case": false,
48
+ "eos_token": "</s>",
49
+ "extra_special_tokens": {},
50
+ "full_tokenizer_file": null,
51
+ "mask_token": "<mask>",
52
+ "max_length": 256,
53
+ "model_max_length": 512,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "<pad>",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
+ "sep_token": "</s>",
59
+ "sp_model_kwargs": {},
60
+ "stride": 128,
61
+ "tokenizer_class": "XLMRobertaTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "only_second",
64
+ "unk_token": "<unk>"
65
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a265a0de87aae5eb11cd3efc056bf622830d469cfcaa1ec8aafda9ceaeeeb539
3
+ size 5304