Hugging Face's logo

uvegesistvan
/
Hun_Eng_RoBERTa_large_Plain

TensorBoard
Safetensors
Hungarian
English
xlm-roberta
Eval Results (legacy)
Model card Files
xet
 Metrics Community
uvegesistvan commited on
Commit
ee76604
·
verified ·
1 Parent(s): 79c2b79

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. XLM-RoBERTa_large_Plain_predictions.xlsx +0 -0
  2. checkpoint-4452/config.json +29 -0
  3. checkpoint-4452/model.safetensors +3 -0
  4. checkpoint-4452/optimizer.pt +3 -0
  5. checkpoint-4452/rng_state.pth +3 -0
  6. checkpoint-4452/scheduler.pt +3 -0
  7. checkpoint-4452/trainer_state.json +118 -0
  8. checkpoint-4452/training_args.bin +3 -0
  9. config.json +29 -0
  10. events.out.tfevents.1728583388.05100af18dbd.2545.0 +3 -0
  11. model.safetensors +3 -0
  12. test_dataset_roberta_large_HUN.xlsx +0 -0
  13. training_args.bin +3 -0
XLM-RoBERTa_large_Plain_predictions.xlsx ADDED
Binary file (126 kB). View file
 
checkpoint-4452/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-4452/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0df55af542412a577a9b75ea788a93ea47a946a7ca961c88bab5e89f2a2eb9
3
+ size 2239618672
checkpoint-4452/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f04633f36d8d4a2847f30286d3dc3dfbb4548a32151bd3a34241a551d43a305
3
+ size 4479472785
checkpoint-4452/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b184440fc6db378ae3b004e94c6200e4f032c71ef078ca92c1837ba3f98affb
3
+ size 14244
checkpoint-4452/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af3d832d51f43cd5d3835fdf31f0538a2455743a8985ef0eaf0c7f51e0f690f3
3
+ size 1064
checkpoint-4452/trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6294568181037903,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/XLM-RoBERTa/checkpoint-4452",
4
+ "epoch": 4.0,
5
+ "eval_steps": 100,
6
+ "global_step": 4452,
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": 9.622591018676758,
14
+ "learning_rate": 4.5e-06,
15
+ "loss": 0.6933,
16
+ "step": 1113
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.590561797752809,
21
+ "eval_f1": 0.6500192086054553,
22
+ "eval_loss": 0.66836017370224,
23
+ "eval_precision": 0.5774744027303754,
24
+ "eval_recall": 0.7434094903339191,
25
+ "eval_runtime": 45.8645,
26
+ "eval_samples_per_second": 48.512,
27
+ "eval_steps_per_second": 3.052,
28
+ "step": 1113
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 28.930395126342773,
33
+ "learning_rate": 4.000000000000001e-06,
34
+ "loss": 0.6451,
35
+ "step": 2226
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.6260674157303371,
40
+ "eval_f1": 0.6521739130434783,
41
+ "eval_loss": 0.6448485851287842,
42
+ "eval_precision": 0.6220095693779905,
43
+ "eval_recall": 0.6854130052724078,
44
+ "eval_runtime": 45.7262,
45
+ "eval_samples_per_second": 48.659,
46
+ "eval_steps_per_second": 3.062,
47
+ "step": 2226
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 33.26604080200195,
52
+ "learning_rate": 3.5e-06,
53
+ "loss": 0.6047,
54
+ "step": 3339
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.635056179775281,
59
+ "eval_f1": 0.6077294685990338,
60
+ "eval_loss": 0.6538584232330322,
61
+ "eval_precision": 0.674892703862661,
62
+ "eval_recall": 0.5527240773286467,
63
+ "eval_runtime": 45.7265,
64
+ "eval_samples_per_second": 48.659,
65
+ "eval_steps_per_second": 3.062,
66
+ "step": 3339
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 33.087928771972656,
71
+ "learning_rate": 3e-06,
72
+ "loss": 0.5614,
73
+ "step": 4452
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.6467415730337078,
78
+ "eval_f1": 0.6689132266217355,
79
+ "eval_loss": 0.6294568181037903,
80
+ "eval_precision": 0.6423948220064725,
81
+ "eval_recall": 0.6977152899824253,
82
+ "eval_runtime": 45.7385,
83
+ "eval_samples_per_second": 48.646,
84
+ "eval_steps_per_second": 3.061,
85
+ "step": 4452
86
+ }
87
+ ],
88
+ "logging_steps": 100,
89
+ "max_steps": 11130,
90
+ "num_input_tokens_seen": 0,
91
+ "num_train_epochs": 10,
92
+ "save_steps": 100,
93
+ "stateful_callbacks": {
94
+ "EarlyStoppingCallback": {
95
+ "args": {
96
+ "early_stopping_patience": 2,
97
+ "early_stopping_threshold": 0.0
98
+ },
99
+ "attributes": {
100
+ "early_stopping_patience_counter": 0
101
+ }
102
+ },
103
+ "TrainerControl": {
104
+ "args": {
105
+ "should_epoch_stop": false,
106
+ "should_evaluate": false,
107
+ "should_log": false,
108
+ "should_save": true,
109
+ "should_training_stop": false
110
+ },
111
+ "attributes": {}
112
+ }
113
+ },
114
+ "total_flos": 6.633860216714035e+16,
115
+ "train_batch_size": 16,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }
checkpoint-4452/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.1728583388.05100af18dbd.2545.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcf70d38d8e04586cdc40c3eefa34b666e539ef3acb8ade6518e6214b75c569c
3
+ size 9443
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0df55af542412a577a9b75ea788a93ea47a946a7ca961c88bab5e89f2a2eb9
3
+ size 2239618672
test_dataset_roberta_large_HUN.xlsx ADDED
Binary file (117 kB). View file
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff238aadf09bba908ff3dfad1141ff451e76dde0b91b1ef88bb5f1889cd5372
3
+ size 5176