Hugging Face's logo

uvegesistvan
/
Hun_RoBERTa_large_Plain

TensorBoard
Safetensors
Hungarian
xlm-roberta
Eval Results
Model card Files Metrics Community
uvegesistvan commited on
Commit
e10a9eb
•
1 Parent(s): ea647e8

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. XLM-RoBERTa_Plain_predictions.xlsx +0 -0
  2. checkpoint-2785/config.json +29 -0
  3. checkpoint-2785/model.safetensors +3 -0
  4. checkpoint-2785/optimizer.pt +3 -0
  5. checkpoint-2785/rng_state.pth +3 -0
  6. checkpoint-2785/scheduler.pt +3 -0
  7. checkpoint-2785/trainer_state.json +137 -0
  8. checkpoint-2785/training_args.bin +3 -0
  9. config.json +29 -0
  10. events.out.tfevents.1728510333.8eb97f4258e4.2986.0 +3 -0
  11. model.safetensors +3 -0
  12. training_args.bin +3 -0
XLM-RoBERTa_Plain_predictions.xlsx ADDED
Binary file (125 kB). View file
 
checkpoint-2785/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "multi_label_classification",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.45.2",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 250002
29
+ }
checkpoint-2785/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64f8353135df2528151f23b417eb9659d0d25a6146b05f2d3ccecbfdc6853ebd
3
+ size 2239618672
checkpoint-2785/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:246fcd24c41137d24f4dfe14a941d811d09a03ff17b3469b9d9c7f0d7648a04f
3
+ size 4479472785
checkpoint-2785/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82cdd0aee70a32f7963591716cf1fe9fd85f2452c997b1d17284ed370fccb55c
3
+ size 14244
checkpoint-2785/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bffa1fa46657ae8a7b5089b9fb12f2cbfd4f93f41eb5e0184d7e6af7f39be42
3
+ size 1064
checkpoint-2785/trainer_state.json ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.570550262928009,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/XLM-RoBERTa/checkpoint-2785",
4
+ "epoch": 5.0,
5
+ "eval_steps": 100,
6
+ "global_step": 2785,
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": 3.1359150409698486,
14
+ "learning_rate": 4.5e-06,
15
+ "loss": 0.6958,
16
+ "step": 557
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5296762589928058,
21
+ "eval_f1": 0.5188592456301748,
22
+ "eval_loss": 0.6925909519195557,
23
+ "eval_precision": 0.5454545454545454,
24
+ "eval_recall": 0.49473684210526314,
25
+ "eval_runtime": 24.1607,
26
+ "eval_samples_per_second": 46.025,
27
+ "eval_steps_per_second": 2.897,
28
+ "step": 557
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 8.246417999267578,
33
+ "learning_rate": 4.000000000000001e-06,
34
+ "loss": 0.6676,
35
+ "step": 1114
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.6519784172661871,
40
+ "eval_f1": 0.7160674981658107,
41
+ "eval_loss": 0.6172838807106018,
42
+ "eval_precision": 0.6153846153846154,
43
+ "eval_recall": 0.856140350877193,
44
+ "eval_runtime": 23.8527,
45
+ "eval_samples_per_second": 46.619,
46
+ "eval_steps_per_second": 2.935,
47
+ "step": 1114
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 68.80496215820312,
52
+ "learning_rate": 3.5e-06,
53
+ "loss": 0.5867,
54
+ "step": 1671
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.6915467625899281,
59
+ "eval_f1": 0.6809302325581396,
60
+ "eval_loss": 0.5942487120628357,
61
+ "eval_precision": 0.7247524752475247,
62
+ "eval_recall": 0.6421052631578947,
63
+ "eval_runtime": 24.0034,
64
+ "eval_samples_per_second": 46.327,
65
+ "eval_steps_per_second": 2.916,
66
+ "step": 1671
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 15.448868751525879,
71
+ "learning_rate": 3e-06,
72
+ "loss": 0.5309,
73
+ "step": 2228
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.7059352517985612,
78
+ "eval_f1": 0.7067264573991031,
79
+ "eval_loss": 0.5705930590629578,
80
+ "eval_precision": 0.7229357798165138,
81
+ "eval_recall": 0.6912280701754386,
82
+ "eval_runtime": 23.8606,
83
+ "eval_samples_per_second": 46.604,
84
+ "eval_steps_per_second": 2.934,
85
+ "step": 2228
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 36.05428695678711,
90
+ "learning_rate": 2.5e-06,
91
+ "loss": 0.4821,
92
+ "step": 2785
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.7140287769784173,
97
+ "eval_f1": 0.741042345276873,
98
+ "eval_loss": 0.570550262928009,
99
+ "eval_precision": 0.6914893617021277,
100
+ "eval_recall": 0.7982456140350878,
101
+ "eval_runtime": 23.8434,
102
+ "eval_samples_per_second": 46.638,
103
+ "eval_steps_per_second": 2.936,
104
+ "step": 2785
105
+ }
106
+ ],
107
+ "logging_steps": 100,
108
+ "max_steps": 5570,
109
+ "num_input_tokens_seen": 0,
110
+ "num_train_epochs": 10,
111
+ "save_steps": 100,
112
+ "stateful_callbacks": {
113
+ "EarlyStoppingCallback": {
114
+ "args": {
115
+ "early_stopping_patience": 2,
116
+ "early_stopping_threshold": 0.0
117
+ },
118
+ "attributes": {
119
+ "early_stopping_patience_counter": 0
120
+ }
121
+ },
122
+ "TrainerControl": {
123
+ "args": {
124
+ "should_epoch_stop": false,
125
+ "should_evaluate": false,
126
+ "should_log": false,
127
+ "should_save": true,
128
+ "should_training_stop": false
129
+ },
130
+ "attributes": {}
131
+ }
132
+ },
133
+ "total_flos": 4.146162635446272e+16,
134
+ "train_batch_size": 16,
135
+ "trial_name": null,
136
+ "trial_params": null
137
+ }
checkpoint-2785/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff238aadf09bba908ff3dfad1141ff451e76dde0b91b1ef88bb5f1889cd5372
3
+ size 5176
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "multi_label_classification",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.45.2",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 250002
29
+ }
events.out.tfevents.1728510333.8eb97f4258e4.2986.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fdac584021969de656dadc498aa11b6eda4965e7b67fe9d83c3b1d0441eb116
3
+ size 10126
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64f8353135df2528151f23b417eb9659d0d25a6146b05f2d3ccecbfdc6853ebd
3
+ size 2239618672
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff238aadf09bba908ff3dfad1141ff451e76dde0b91b1ef88bb5f1889cd5372
3
+ size 5176