Hugging Face's logo

uvegesistvan
/
optimized_proposal_1

Text Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
Model card Files
xet
Metrics Community
uvegesistvan commited on
Commit
c7c1ecc
·
verified ·
1 Parent(s): e7b951b

Upload folder using huggingface_hub

Browse files
Files changed (38) hide show
  1. .gitattributes +1 -0
  2. checkpoint-52920/config.json +50 -0
  3. checkpoint-52920/model.safetensors +3 -0
  4. checkpoint-52920/optimizer.pt +3 -0
  5. checkpoint-52920/rng_state.pth +3 -0
  6. checkpoint-52920/scheduler.pt +3 -0
  7. checkpoint-52920/trainer_state.json +108 -0
  8. checkpoint-52920/training_args.bin +3 -0
  9. checkpoint-88200/config.json +50 -0
  10. checkpoint-88200/model.safetensors +3 -0
  11. checkpoint-88200/optimizer.pt +3 -0
  12. checkpoint-88200/rng_state.pth +3 -0
  13. checkpoint-88200/scheduler.pt +3 -0
  14. checkpoint-88200/trainer_state.json +152 -0
  15. checkpoint-88200/training_args.bin +3 -0
  16. config.json +50 -0
  17. logs/events.out.tfevents.1740669087.e5f5ecbc2a6a.667.0 +3 -0
  18. logs/events.out.tfevents.1740673452.e5f5ecbc2a6a.667.1 +3 -0
  19. logs/events.out.tfevents.1740679362.e5f5ecbc2a6a.667.2 +3 -0
  20. logs/events.out.tfevents.1740685646.e5f5ecbc2a6a.667.3 +3 -0
  21. logs/events.out.tfevents.1740690070.e5f5ecbc2a6a.667.4 +3 -0
  22. logs/events.out.tfevents.1740702465.e0aeb2389750.18222.0 +3 -0
  23. logs/events.out.tfevents.1740702611.50e4ec551393.550.0 +3 -0
  24. logs/events.out.tfevents.1740707667.50e4ec551393.550.1 +3 -0
  25. logs/events.out.tfevents.1740716163.50e4ec551393.550.2 +3 -0
  26. logs/events.out.tfevents.1740717905.50e4ec551393.550.3 +3 -0
  27. logs/events.out.tfevents.1740731088.50e4ec551393.550.4 +3 -0
  28. logs/events.out.tfevents.1740738000.50e4ec551393.550.5 +3 -0
  29. logs/events.out.tfevents.1740741631.50e4ec551393.550.6 +3 -0
  30. logs/events.out.tfevents.1740749903.50e4ec551393.550.7 +3 -0
  31. logs/events.out.tfevents.1740756407.50e4ec551393.550.8 +3 -0
  32. logs/events.out.tfevents.1740769378.50e4ec551393.550.9 +3 -0
  33. logs/events.out.tfevents.1740781279.50e4ec551393.550.10 +3 -0
  34. model.safetensors +3 -0
  35. special_tokens_map.json +15 -0
  36. tokenizer.json +3 -0
  37. tokenizer_config.json +55 -0
  38. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-52920/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
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
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 4096,
26
+ "label2id": {
27
+ "LABEL_0": 0,
28
+ "LABEL_1": 1,
29
+ "LABEL_2": 2,
30
+ "LABEL_3": 3,
31
+ "LABEL_4": 4,
32
+ "LABEL_5": 5,
33
+ "LABEL_6": 6,
34
+ "LABEL_7": 7,
35
+ "LABEL_8": 8
36
+ },
37
+ "layer_norm_eps": 1e-05,
38
+ "max_position_embeddings": 514,
39
+ "model_type": "xlm-roberta",
40
+ "num_attention_heads": 16,
41
+ "num_hidden_layers": 24,
42
+ "output_past": true,
43
+ "pad_token_id": 1,
44
+ "position_embedding_type": "absolute",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.49.0",
47
+ "type_vocab_size": 1,
48
+ "use_cache": true,
49
+ "vocab_size": 250002
50
+ }
checkpoint-52920/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6456e2d068c216dfbae8a2a45fb0521dbbf66d84ecb8a3420df1ab139e92221e
3
+ size 2239647372
checkpoint-52920/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fb4b2ab1ef4e16dd768513cba2055b24affd9027f8e970d05f0aa135473e740
3
+ size 4479530129
checkpoint-52920/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae94289004bf7b8e3e638a88abc39c68a1f8e006a8aff098387cdc04cf8bc128
3
+ size 14244
checkpoint-52920/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:453d37537c96afa234ac1a4dbcb8dc3b01513b54dd8d5bf050c0230d0f4d2951
3
+ size 1064
checkpoint-52920/trainer_state.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5593105349247343,
3
+ "best_model_checkpoint": "model/checkpoint-52920",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 52920,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 50.548851013183594,
14
+ "learning_rate": 4.5246352478135424e-06,
15
+ "loss": 1.5427,
16
+ "step": 17640
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5058956916099773,
21
+ "eval_f1_macro": 0.5205801166115408,
22
+ "eval_f1_weighted": 0.49617134581102434,
23
+ "eval_loss": 1.5204957723617554,
24
+ "eval_precision_macro": 0.5811975776248032,
25
+ "eval_precision_weighted": 0.5725457955618433,
26
+ "eval_recall_macro": 0.5336316110063488,
27
+ "eval_recall_weighted": 0.5058956916099773,
28
+ "eval_runtime": 90.4124,
29
+ "eval_samples_per_second": 48.776,
30
+ "eval_steps_per_second": 24.388,
31
+ "step": 17640
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "grad_norm": 34.12895202636719,
36
+ "learning_rate": 3.2750841586103932e-06,
37
+ "loss": 1.3601,
38
+ "step": 35280
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "eval_accuracy": 0.5390022675736962,
43
+ "eval_f1_macro": 0.5526684923116755,
44
+ "eval_f1_weighted": 0.5363903680411256,
45
+ "eval_loss": 1.4914500713348389,
46
+ "eval_precision_macro": 0.5690443791451115,
47
+ "eval_precision_weighted": 0.5437222363835312,
48
+ "eval_recall_macro": 0.5477102309891048,
49
+ "eval_recall_weighted": 0.5390022675736962,
50
+ "eval_runtime": 92.1119,
51
+ "eval_samples_per_second": 47.877,
52
+ "eval_steps_per_second": 23.938,
53
+ "step": 35280
54
+ },
55
+ {
56
+ "epoch": 3.0,
57
+ "grad_norm": 9.428272247314453,
58
+ "learning_rate": 1.7291524533131918e-06,
59
+ "loss": 1.2854,
60
+ "step": 52920
61
+ },
62
+ {
63
+ "epoch": 3.0,
64
+ "eval_accuracy": 0.546031746031746,
65
+ "eval_f1_macro": 0.5593105349247343,
66
+ "eval_f1_weighted": 0.5404116337093552,
67
+ "eval_loss": 1.6935405731201172,
68
+ "eval_precision_macro": 0.563042729738896,
69
+ "eval_precision_weighted": 0.5453144110800754,
70
+ "eval_recall_macro": 0.5628661101651561,
71
+ "eval_recall_weighted": 0.546031746031746,
72
+ "eval_runtime": 92.7796,
73
+ "eval_samples_per_second": 47.532,
74
+ "eval_steps_per_second": 23.766,
75
+ "step": 52920
76
+ }
77
+ ],
78
+ "logging_steps": 500,
79
+ "max_steps": 88200,
80
+ "num_input_tokens_seen": 0,
81
+ "num_train_epochs": 5,
82
+ "save_steps": 500,
83
+ "stateful_callbacks": {
84
+ "EarlyStoppingCallback": {
85
+ "args": {
86
+ "early_stopping_patience": 2,
87
+ "early_stopping_threshold": 0.0
88
+ },
89
+ "attributes": {
90
+ "early_stopping_patience_counter": 0
91
+ }
92
+ },
93
+ "TrainerControl": {
94
+ "args": {
95
+ "should_epoch_stop": false,
96
+ "should_evaluate": false,
97
+ "should_log": false,
98
+ "should_save": true,
99
+ "should_training_stop": false
100
+ },
101
+ "attributes": {}
102
+ }
103
+ },
104
+ "total_flos": 4.931897418878976e+16,
105
+ "train_batch_size": 2,
106
+ "trial_name": null,
107
+ "trial_params": null
108
+ }
checkpoint-52920/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b5c8cbd5da632b32e03f38255da1b60850a45befb04284808b91121020c0053
3
+ size 5240
checkpoint-88200/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
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
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 4096,
26
+ "label2id": {
27
+ "LABEL_0": 0,
28
+ "LABEL_1": 1,
29
+ "LABEL_2": 2,
30
+ "LABEL_3": 3,
31
+ "LABEL_4": 4,
32
+ "LABEL_5": 5,
33
+ "LABEL_6": 6,
34
+ "LABEL_7": 7,
35
+ "LABEL_8": 8
36
+ },
37
+ "layer_norm_eps": 1e-05,
38
+ "max_position_embeddings": 514,
39
+ "model_type": "xlm-roberta",
40
+ "num_attention_heads": 16,
41
+ "num_hidden_layers": 24,
42
+ "output_past": true,
43
+ "pad_token_id": 1,
44
+ "position_embedding_type": "absolute",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.49.0",
47
+ "type_vocab_size": 1,
48
+ "use_cache": true,
49
+ "vocab_size": 250002
50
+ }
checkpoint-88200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3826b94cd38e0931e7530ff8a39bab0179a023b90cc7f04de8d84f891eaffa6
3
+ size 2239647372
checkpoint-88200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d009a0c50bbae61468ec5408f73f621941a0f7d3f57dd2bf9ea72c4467e85ae6
3
+ size 4479530129
checkpoint-88200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29d71e08cfb61cec61ddff222211f4c41dd52b4402e7141fbfe09ae21e7b4807
3
+ size 14244
checkpoint-88200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d883a4027dbbdcabcc0d4ad9798bfbd5bbddffb4250392183cac000ee97ab69
3
+ size 1064
checkpoint-88200/trainer_state.json ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5593105349247343,
3
+ "best_model_checkpoint": "model/checkpoint-52920",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 88200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 50.548851013183594,
14
+ "learning_rate": 4.5246352478135424e-06,
15
+ "loss": 1.5427,
16
+ "step": 17640
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5058956916099773,
21
+ "eval_f1_macro": 0.5205801166115408,
22
+ "eval_f1_weighted": 0.49617134581102434,
23
+ "eval_loss": 1.5204957723617554,
24
+ "eval_precision_macro": 0.5811975776248032,
25
+ "eval_precision_weighted": 0.5725457955618433,
26
+ "eval_recall_macro": 0.5336316110063488,
27
+ "eval_recall_weighted": 0.5058956916099773,
28
+ "eval_runtime": 90.4124,
29
+ "eval_samples_per_second": 48.776,
30
+ "eval_steps_per_second": 24.388,
31
+ "step": 17640
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "grad_norm": 34.12895202636719,
36
+ "learning_rate": 3.2750841586103932e-06,
37
+ "loss": 1.3601,
38
+ "step": 35280
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "eval_accuracy": 0.5390022675736962,
43
+ "eval_f1_macro": 0.5526684923116755,
44
+ "eval_f1_weighted": 0.5363903680411256,
45
+ "eval_loss": 1.4914500713348389,
46
+ "eval_precision_macro": 0.5690443791451115,
47
+ "eval_precision_weighted": 0.5437222363835312,
48
+ "eval_recall_macro": 0.5477102309891048,
49
+ "eval_recall_weighted": 0.5390022675736962,
50
+ "eval_runtime": 92.1119,
51
+ "eval_samples_per_second": 47.877,
52
+ "eval_steps_per_second": 23.938,
53
+ "step": 35280
54
+ },
55
+ {
56
+ "epoch": 3.0,
57
+ "grad_norm": 9.428272247314453,
58
+ "learning_rate": 1.7291524533131918e-06,
59
+ "loss": 1.2854,
60
+ "step": 52920
61
+ },
62
+ {
63
+ "epoch": 3.0,
64
+ "eval_accuracy": 0.546031746031746,
65
+ "eval_f1_macro": 0.5593105349247343,
66
+ "eval_f1_weighted": 0.5404116337093552,
67
+ "eval_loss": 1.6935405731201172,
68
+ "eval_precision_macro": 0.563042729738896,
69
+ "eval_precision_weighted": 0.5453144110800754,
70
+ "eval_recall_macro": 0.5628661101651561,
71
+ "eval_recall_weighted": 0.546031746031746,
72
+ "eval_runtime": 92.7796,
73
+ "eval_samples_per_second": 47.532,
74
+ "eval_steps_per_second": 23.766,
75
+ "step": 52920
76
+ },
77
+ {
78
+ "epoch": 4.0,
79
+ "grad_norm": 2.4480783939361572,
80
+ "learning_rate": 4.779813469311145e-07,
81
+ "loss": 1.2134,
82
+ "step": 70560
83
+ },
84
+ {
85
+ "epoch": 4.0,
86
+ "eval_accuracy": 0.5424036281179139,
87
+ "eval_f1_macro": 0.556857581435203,
88
+ "eval_f1_weighted": 0.540084379855431,
89
+ "eval_loss": 1.850308895111084,
90
+ "eval_precision_macro": 0.5534590158556113,
91
+ "eval_precision_weighted": 0.5403231343551113,
92
+ "eval_recall_macro": 0.5627436062490211,
93
+ "eval_recall_weighted": 0.5424036281179139,
94
+ "eval_runtime": 90.1464,
95
+ "eval_samples_per_second": 48.92,
96
+ "eval_steps_per_second": 24.46,
97
+ "step": 70560
98
+ },
99
+ {
100
+ "epoch": 5.0,
101
+ "grad_norm": 97.99571228027344,
102
+ "learning_rate": 0.0,
103
+ "loss": 1.1551,
104
+ "step": 88200
105
+ },
106
+ {
107
+ "epoch": 5.0,
108
+ "eval_accuracy": 0.5380952380952381,
109
+ "eval_f1_macro": 0.5523656911346606,
110
+ "eval_f1_weighted": 0.535792504428007,
111
+ "eval_loss": 1.9902939796447754,
112
+ "eval_precision_macro": 0.5460891197767054,
113
+ "eval_precision_weighted": 0.5351070225287136,
114
+ "eval_recall_macro": 0.5601702556233763,
115
+ "eval_recall_weighted": 0.5380952380952381,
116
+ "eval_runtime": 89.9788,
117
+ "eval_samples_per_second": 49.012,
118
+ "eval_steps_per_second": 24.506,
119
+ "step": 88200
120
+ }
121
+ ],
122
+ "logging_steps": 500,
123
+ "max_steps": 88200,
124
+ "num_input_tokens_seen": 0,
125
+ "num_train_epochs": 5,
126
+ "save_steps": 500,
127
+ "stateful_callbacks": {
128
+ "EarlyStoppingCallback": {
129
+ "args": {
130
+ "early_stopping_patience": 2,
131
+ "early_stopping_threshold": 0.0
132
+ },
133
+ "attributes": {
134
+ "early_stopping_patience_counter": 2
135
+ }
136
+ },
137
+ "TrainerControl": {
138
+ "args": {
139
+ "should_epoch_stop": false,
140
+ "should_evaluate": false,
141
+ "should_log": false,
142
+ "should_save": true,
143
+ "should_training_stop": true
144
+ },
145
+ "attributes": {}
146
+ }
147
+ },
148
+ "total_flos": 8.21982903146496e+16,
149
+ "train_batch_size": 2,
150
+ "trial_name": null,
151
+ "trial_params": null
152
+ }
checkpoint-88200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b5c8cbd5da632b32e03f38255da1b60850a45befb04284808b91121020c0053
3
+ size 5240
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
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
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 4096,
26
+ "label2id": {
27
+ "LABEL_0": 0,
28
+ "LABEL_1": 1,
29
+ "LABEL_2": 2,
30
+ "LABEL_3": 3,
31
+ "LABEL_4": 4,
32
+ "LABEL_5": 5,
33
+ "LABEL_6": 6,
34
+ "LABEL_7": 7,
35
+ "LABEL_8": 8
36
+ },
37
+ "layer_norm_eps": 1e-05,
38
+ "max_position_embeddings": 514,
39
+ "model_type": "xlm-roberta",
40
+ "num_attention_heads": 16,
41
+ "num_hidden_layers": 24,
42
+ "output_past": true,
43
+ "pad_token_id": 1,
44
+ "position_embedding_type": "absolute",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.49.0",
47
+ "type_vocab_size": 1,
48
+ "use_cache": true,
49
+ "vocab_size": 250002
50
+ }
logs/events.out.tfevents.1740669087.e5f5ecbc2a6a.667.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36a707ddcfa664f3d77d8c820db6eef73581eec03f88772430412647ffcc0753
3
+ size 10170
logs/events.out.tfevents.1740673452.e5f5ecbc2a6a.667.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96132ab8f7f228b064195484f557a6871b340562667460f290f98c42f63da45
3
+ size 10191
logs/events.out.tfevents.1740679362.e5f5ecbc2a6a.667.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1ba8f2fa76fb4e86910f1e0746bc65441c04536ac8a4929f00a5ea57ec5e4d9
3
+ size 8438
logs/events.out.tfevents.1740685646.e5f5ecbc2a6a.667.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9487d548ae4d3f586b1f0559566ef86447e0ade1351170e1ee92e83c555659d2
3
+ size 9294
logs/events.out.tfevents.1740690070.e5f5ecbc2a6a.667.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:219700a2e1b6c212320c3296c1a9ed6a53892d4e8d7829c3ea98cc4e519a323e
3
+ size 8065
logs/events.out.tfevents.1740702465.e0aeb2389750.18222.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93736d1f540a31348c727ece03dd4261529939d64978baa46c1f402f90fee3a6
3
+ size 5428
logs/events.out.tfevents.1740702611.50e4ec551393.550.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f7192ceab6b932836d0ba45a7ef4b29fb8ffe75b86a7329c1b377e16952ee4
3
+ size 8414
logs/events.out.tfevents.1740707667.50e4ec551393.550.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cbe65213748dd13b00a9562ea5a017bba82cf941724f8db7221ae75ad2e2384
3
+ size 10170
logs/events.out.tfevents.1740716163.50e4ec551393.550.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb586dde98d3e8adfaa40a3d27e3fec405ef0053c6349c9f3e4b46294a206e2
3
+ size 6662
logs/events.out.tfevents.1740717905.50e4ec551393.550.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a1d630158e4ccaabc624c8bd58f29219a73a17be58bc323c68a4a15f49a17c
3
+ size 10171
logs/events.out.tfevents.1740731088.50e4ec551393.550.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3d166a496685bab53456f03fd55dc52be439ce97f6ee4d210139a9f7e6c2ec5
3
+ size 10207
logs/events.out.tfevents.1740738000.50e4ec551393.550.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a197dbd3d6c33cf35341ade85a6ced3da3ae9d746ffeaf6a033a6930673c0c22
3
+ size 9292
logs/events.out.tfevents.1740741631.50e4ec551393.550.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e21accfd7bac7d5ecbe016c7d9de94f52cc1153d03838ef6b1dd9dda7bc88b29
3
+ size 8416
logs/events.out.tfevents.1740749903.50e4ec551393.550.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7443d03e25dab41c2ced8e4a1b83244c6a5a7c770de926e50ce0ff1ae0d13b46
3
+ size 8413
logs/events.out.tfevents.1740756407.50e4ec551393.550.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eed088ca1e46968f23a32a4e90e54af4e69ccbad5dd5446d0dbf45d00ddb726
3
+ size 10172
logs/events.out.tfevents.1740769378.50e4ec551393.550.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7194a87e2075ae448ec869f9072c45d36a71dbd2f0eba232cbe214b0dcaf7838
3
+ size 10209
logs/events.out.tfevents.1740781279.50e4ec551393.550.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eca645b35d0609605acd45df77f57ddf8abbb8a3353e16402cab49a75810e09
3
+ size 10257
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6456e2d068c216dfbae8a2a45fb0521dbbf66d84ecb8a3420df1ab139e92221e
3
+ size 2239647372
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93189c5d9a15db043017cfd920e00cf72fe9a4220bd74b460b635f6aa85a61a2
3
+ size 17082999
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
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
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b5c8cbd5da632b32e03f38255da1b60850a45befb04284808b91121020c0053
3
+ size 5240