Hugging Face's logo

uvegesistvan
/
Hun_RoBERTa_Plain

Text Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
Inference Endpoints
Model card Files Metrics Community
uvegesistvan commited on
Commit
1cf5a24
•
1 Parent(s): 78b3664

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. checkpoint-2228/config.json +29 -0
  2. checkpoint-2228/model.safetensors +3 -0
  3. checkpoint-2228/optimizer.pt +3 -0
  4. checkpoint-2228/rng_state.pth +3 -0
  5. checkpoint-2228/scheduler.pt +3 -0
  6. checkpoint-2228/trainer_state.json +118 -0
  7. checkpoint-2228/training_args.bin +3 -0
  8. config.json +29 -0
  9. events.out.tfevents.1718577042.be0cc0ed6497.1106.0 +3 -0
  10. events.out.tfevents.1718577662.950880a0be73.1927.0 +3 -0
  11. events.out.tfevents.1718627892.8984a4f84e25.327.0 +3 -0
  12. events.out.tfevents.1718631240.8984a4f84e25.327.1 +3 -0
  13. events.out.tfevents.1718631292.8984a4f84e25.327.2 +3 -0
  14. events.out.tfevents.1718631516.a0a1dd925225.1169.0 +3 -0
  15. events.out.tfevents.1718633445.6c20ef9bbb1b.1855.0 +3 -0
  16. events.out.tfevents.1718645415.198ec9b4992b.765.0 +3 -0
  17. model.safetensors +3 -0
  18. training_args.bin +3 -0
checkpoint-2228/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": "4.41.2",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 250002
29
+ }
checkpoint-2228/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d658b1cd1eec1c948cbf2be49ac4f3918d7455f99ac4cd48636bca92b492e5
3
+ size 1112205008
checkpoint-2228/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c53f4ccd7d451956c547c96dade856251ea1f82f227511d2ef4835db342424f6
3
+ size 2224529658
checkpoint-2228/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e4e26563fe753793350ce6ac4c64e029076fd4e33ee57666bfb455636909558
3
+ size 14244
checkpoint-2228/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:132d3f37c666f33bf034b4d88888c8fcb42f610c5bc83d70a9cf0505fe78a1a9
3
+ size 1064
checkpoint-2228/trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6202902793884277,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/XLM-RoBERTa/checkpoint-2228",
4
+ "epoch": 4.0,
5
+ "eval_steps": 100,
6
+ "global_step": 2228,
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": 3.233938455581665,
14
+ "learning_rate": 4.5e-06,
15
+ "loss": 0.6924,
16
+ "step": 557
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5845323741007195,
21
+ "eval_f1": 0.5700593887306262,
22
+ "eval_loss": 0.6825495362281799,
23
+ "eval_precision": 0.5918083714846305,
24
+ "eval_recall": 0.5845323741007195,
25
+ "eval_runtime": 20.2766,
26
+ "eval_samples_per_second": 54.841,
27
+ "eval_steps_per_second": 3.452,
28
+ "step": 557
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 11.896564483642578,
33
+ "learning_rate": 4.000000000000001e-06,
34
+ "loss": 0.6591,
35
+ "step": 1114
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.6312949640287769,
40
+ "eval_f1": 0.6239247956941143,
41
+ "eval_loss": 0.6512733697891235,
42
+ "eval_precision": 0.6380170358095547,
43
+ "eval_recall": 0.6312949640287769,
44
+ "eval_runtime": 20.0342,
45
+ "eval_samples_per_second": 55.505,
46
+ "eval_steps_per_second": 3.494,
47
+ "step": 1114
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 43.97391891479492,
52
+ "learning_rate": 3.5e-06,
53
+ "loss": 0.612,
54
+ "step": 1671
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.6501798561151079,
59
+ "eval_f1": 0.6501331764249932,
60
+ "eval_loss": 0.663809597492218,
61
+ "eval_precision": 0.6512329296145304,
62
+ "eval_recall": 0.6501798561151079,
63
+ "eval_runtime": 20.05,
64
+ "eval_samples_per_second": 55.461,
65
+ "eval_steps_per_second": 3.491,
66
+ "step": 1671
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 77.9683609008789,
71
+ "learning_rate": 3e-06,
72
+ "loss": 0.5806,
73
+ "step": 2228
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.6555755395683454,
78
+ "eval_f1": 0.6533033008167716,
79
+ "eval_loss": 0.6202902793884277,
80
+ "eval_precision": 0.6574073781808177,
81
+ "eval_recall": 0.6555755395683454,
82
+ "eval_runtime": 20.019,
83
+ "eval_samples_per_second": 55.547,
84
+ "eval_steps_per_second": 3.497,
85
+ "step": 2228
86
+ }
87
+ ],
88
+ "logging_steps": 100,
89
+ "max_steps": 5570,
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": 9364648682373120.0,
115
+ "train_batch_size": 16,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }
checkpoint-2228/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee675c9042233338b4c7e9604f8e218d236a37fca7cee0b158407a995c9d93a
3
+ size 5048
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": "4.41.2",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 250002
29
+ }
events.out.tfevents.1718577042.be0cc0ed6497.1106.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f1419ec5bed75281bf566138bc14216545db98477dc1f124532da8be6069de
3
+ size 88
events.out.tfevents.1718577662.950880a0be73.1927.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af3d539416c86ff507b2731e58c7f0cb35d1d155588854b149d1839e44770a36
3
+ size 10606
events.out.tfevents.1718627892.8984a4f84e25.327.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9295460f538fde3179cde5b6db35637e49a69b0fbacb0ec17ed0c139eaf42dd6
3
+ size 8470
events.out.tfevents.1718631240.8984a4f84e25.327.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f94f029ea6dba2394206d2952555c4d5bbf121a3dd7e73e057eb67cfa660d3a4
3
+ size 88
events.out.tfevents.1718631292.8984a4f84e25.327.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88a7c9b7b53f4f15a64ca228e4f8a33376411bd0e0a94feb84fbb25b1f9a36d2
3
+ size 88
events.out.tfevents.1718631516.a0a1dd925225.1169.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:191e32606e1d10c5de8978792017a08216741ae557cc4a7393e5fb0395d2a80e
3
+ size 5595
events.out.tfevents.1718633445.6c20ef9bbb1b.1855.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94ba67062f5b459779f91cdf1a81b0a21550623b6156a25dce27001f364004aa
3
+ size 6278
events.out.tfevents.1718645415.198ec9b4992b.765.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f4d6752722394086e57edecdc105c8297768eb6e72e409ff8047c7b11197e7
3
+ size 9364
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d658b1cd1eec1c948cbf2be49ac4f3918d7455f99ac4cd48636bca92b492e5
3
+ size 1112205008
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee675c9042233338b4c7e9604f8e218d236a37fca7cee0b158407a995c9d93a
3
+ size 5048