Hugging Face's logo

uvegesistvan
/
Hun_RoBERTa_base_Plain

TensorBoard
Safetensors
Hungarian
xlm-roberta
Eval Results
Model card Files Metrics Community
uvegesistvan commited on
Commit
20bcd97
•
1 Parent(s): 9176649

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. checkpoint-2785/config.json +29 -0
  2. checkpoint-2785/model.safetensors +3 -0
  3. checkpoint-2785/optimizer.pt +3 -0
  4. checkpoint-2785/rng_state.pth +3 -0
  5. checkpoint-2785/scheduler.pt +3 -0
  6. checkpoint-2785/trainer_state.json +137 -0
  7. checkpoint-2785/training_args.bin +3 -0
  8. config.json +29 -0
  9. events.out.tfevents.1728501299.fb2369aaeb57.2738.1 +3 -0
  10. model.safetensors +3 -0
  11. training_args.bin +3 -0
checkpoint-2785/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
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": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
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 sha256:99130d1edc42965036f1ee2b8af40ff4072568a5e48be8b7a1f32cb5f3c00250
3
+ size 1112205008
checkpoint-2785/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65d00befa8866754d7f6dfb62e0c7316ff3f0c43a4e9e2faabbb9568d4b22fc6
3
+ size 2224529658
checkpoint-2785/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cae3161d81febe352c7ac6e486d8e5109eecf3bea13eecadc6c6c880b021ce4e
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": 0.6230994462966919,
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": 5.293243408203125,
14
+ "learning_rate": 4.5e-06,
15
+ "loss": 0.6948,
16
+ "step": 557
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5242805755395683,
21
+ "eval_f1": 0.6641269841269841,
22
+ "eval_loss": 0.690502405166626,
23
+ "eval_precision": 0.5203980099502488,
24
+ "eval_recall": 0.9175438596491228,
25
+ "eval_runtime": 8.9725,
26
+ "eval_samples_per_second": 123.935,
27
+ "eval_steps_per_second": 7.802,
28
+ "step": 557
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 4.867625713348389,
33
+ "learning_rate": 4.000000000000001e-06,
34
+ "loss": 0.6886,
35
+ "step": 1114
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.5683453237410072,
40
+ "eval_f1": 0.6536796536796536,
41
+ "eval_loss": 0.6837959289550781,
42
+ "eval_precision": 0.5551470588235294,
43
+ "eval_recall": 0.7947368421052632,
44
+ "eval_runtime": 8.6635,
45
+ "eval_samples_per_second": 128.354,
46
+ "eval_steps_per_second": 8.08,
47
+ "step": 1114
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 12.451358795166016,
52
+ "learning_rate": 3.5e-06,
53
+ "loss": 0.6696,
54
+ "step": 1671
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.5926258992805755,
59
+ "eval_f1": 0.6091458153580673,
60
+ "eval_loss": 0.6735815405845642,
61
+ "eval_precision": 0.599320882852292,
62
+ "eval_recall": 0.6192982456140351,
63
+ "eval_runtime": 8.6269,
64
+ "eval_samples_per_second": 128.899,
65
+ "eval_steps_per_second": 8.114,
66
+ "step": 1671
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 11.778752326965332,
71
+ "learning_rate": 3e-06,
72
+ "loss": 0.6372,
73
+ "step": 2228
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.6402877697841727,
78
+ "eval_f1": 0.6683250414593698,
79
+ "eval_loss": 0.6366727352142334,
80
+ "eval_precision": 0.6336477987421384,
81
+ "eval_recall": 0.7070175438596491,
82
+ "eval_runtime": 8.6235,
83
+ "eval_samples_per_second": 128.95,
84
+ "eval_steps_per_second": 8.117,
85
+ "step": 2228
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 15.772424697875977,
90
+ "learning_rate": 2.5e-06,
91
+ "loss": 0.6001,
92
+ "step": 2785
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.6555755395683454,
97
+ "eval_f1": 0.6706792777300086,
98
+ "eval_loss": 0.6230994462966919,
99
+ "eval_precision": 0.657672849915683,
100
+ "eval_recall": 0.6842105263157895,
101
+ "eval_runtime": 8.6356,
102
+ "eval_samples_per_second": 128.77,
103
+ "eval_steps_per_second": 8.106,
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": 1.17058108529664e+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-base",
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": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
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.1728501299.fb2369aaeb57.2738.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e09ded96b0ff424dd16ce79b420b4b0125872b32d3f6d9e91de9a6534254b2
3
+ size 10124
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99130d1edc42965036f1ee2b8af40ff4072568a5e48be8b7a1f32cb5f3c00250
3
+ size 1112205008
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff238aadf09bba908ff3dfad1141ff451e76dde0b91b1ef88bb5f1889cd5372
3
+ size 5176