Hugging Face's logo

uvegesistvan
/
guilt-roberta-large

Text Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
Model card Files
xet
Metrics Community
uvegesistvan commited on
Commit
40dc61f
·
verified ·
1 Parent(s): d1f96f0

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. .gitattributes +1 -0
  2. checkpoint-1024/config.json +28 -0
  3. checkpoint-1024/model.safetensors +3 -0
  4. checkpoint-1024/optimizer.pt +3 -0
  5. checkpoint-1024/rng_state.pth +3 -0
  6. checkpoint-1024/scheduler.pt +3 -0
  7. checkpoint-1024/trainer_state.json +86 -0
  8. checkpoint-1024/training_args.bin +3 -0
  9. checkpoint-2048/config.json +28 -0
  10. checkpoint-2048/model.safetensors +3 -0
  11. checkpoint-2048/optimizer.pt +3 -0
  12. checkpoint-2048/rng_state.pth +3 -0
  13. checkpoint-2048/scheduler.pt +3 -0
  14. checkpoint-2048/trainer_state.json +130 -0
  15. checkpoint-2048/training_args.bin +3 -0
  16. config.json +28 -0
  17. logs/events.out.tfevents.1740652331.686e763fa1a3.6372.0 +3 -0
  18. logs/events.out.tfevents.1740652422.686e763fa1a3.6372.1 +3 -0
  19. model.safetensors +3 -0
  20. special_tokens_map.json +15 -0
  21. tokenizer.json +3 -0
  22. tokenizer_config.json +55 -0
  23. 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-1024/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.49.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
checkpoint-1024/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a194e4caa903e2cc9a968fcee5892a44a70812c34b5fd6bcb2c94bd873271e26
3
+ size 2239618672
checkpoint-1024/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04fe8c6a0cdc80052d4edd41173c68a0cb3b00cb06d18603e3dff4fca640c9e9
3
+ size 4479472785
checkpoint-1024/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecb13755a864f8dee7fddec93c388dd3980f7ce7191684cc8a6907c340c0f7ce
3
+ size 14244
checkpoint-1024/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1207f9ebb51e5a419c3af92c9b5c1dc262ba06ac06c677c8a33f76879c126163
3
+ size 1064
checkpoint-1024/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9765567765567765,
3
+ "best_model_checkpoint": "model/checkpoint-1024",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1024,
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": 0.062136758118867874,
14
+ "learning_rate": 1.9363439581125603e-05,
15
+ "loss": 0.1384,
16
+ "step": 512
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.93359375,
21
+ "eval_f1_macro": 0.9335684083589015,
22
+ "eval_f1_weighted": 0.9335582717024622,
23
+ "eval_loss": 0.10384641587734222,
24
+ "eval_precision_macro": 0.9347320773183263,
25
+ "eval_precision_weighted": 0.9349217985380474,
26
+ "eval_recall_macro": 0.9338033327229445,
27
+ "eval_recall_weighted": 0.93359375,
28
+ "eval_runtime": 9.4737,
29
+ "eval_samples_per_second": 27.022,
30
+ "eval_steps_per_second": 6.756,
31
+ "step": 512
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "grad_norm": 5.7770538330078125,
36
+ "learning_rate": 1.7273933762797558e-05,
37
+ "loss": 0.0833,
38
+ "step": 1024
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "eval_accuracy": 0.9765625,
43
+ "eval_f1_macro": 0.9765567765567765,
44
+ "eval_f1_weighted": 0.9765596382783882,
45
+ "eval_loss": 0.05563850328326225,
46
+ "eval_precision_macro": 0.9767328244274809,
47
+ "eval_precision_weighted": 0.9766760496183207,
48
+ "eval_recall_macro": 0.9765000305194409,
49
+ "eval_recall_weighted": 0.9765625,
50
+ "eval_runtime": 9.4836,
51
+ "eval_samples_per_second": 26.994,
52
+ "eval_steps_per_second": 6.748,
53
+ "step": 1024
54
+ }
55
+ ],
56
+ "logging_steps": 500,
57
+ "max_steps": 4096,
58
+ "num_input_tokens_seen": 0,
59
+ "num_train_epochs": 8,
60
+ "save_steps": 500,
61
+ "stateful_callbacks": {
62
+ "EarlyStoppingCallback": {
63
+ "args": {
64
+ "early_stopping_patience": 2,
65
+ "early_stopping_threshold": 0.0
66
+ },
67
+ "attributes": {
68
+ "early_stopping_patience_counter": 0
69
+ }
70
+ },
71
+ "TrainerControl": {
72
+ "args": {
73
+ "should_epoch_stop": false,
74
+ "should_evaluate": false,
75
+ "should_log": false,
76
+ "should_save": true,
77
+ "should_training_stop": false
78
+ },
79
+ "attributes": {}
80
+ }
81
+ },
82
+ "total_flos": 3813463138738176.0,
83
+ "train_batch_size": 4,
84
+ "trial_name": null,
85
+ "trial_params": null
86
+ }
checkpoint-1024/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05f014aae6457a5193b7b97676fb49f1f8e5a4d72875fe8b03696e481f3aa324
3
+ size 5240
checkpoint-2048/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.49.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
checkpoint-2048/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ec1c925d4ebc0b4487bd2af17fb9d768ad8e08abedb8360d221d6c01b49180
3
+ size 2239618672
checkpoint-2048/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc1a8fa968b2a282750e9d7fa97a0638d4cd182deff6ea2b7c0d66e857ac1ad
3
+ size 4479472785
checkpoint-2048/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dab696f099f9aaba84af3bfd6d5ad35ed46f8eb262669e02ab70c95d26b7a8e
3
+ size 14244
checkpoint-2048/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9230b238c7f6c83c2c2208411aa9c61e3f92b0235be4a40f7921eef6210e28f0
3
+ size 1064
checkpoint-2048/trainer_state.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9765567765567765,
3
+ "best_model_checkpoint": "model/checkpoint-1024",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2048,
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": 0.062136758118867874,
14
+ "learning_rate": 1.9363439581125603e-05,
15
+ "loss": 0.1384,
16
+ "step": 512
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.93359375,
21
+ "eval_f1_macro": 0.9335684083589015,
22
+ "eval_f1_weighted": 0.9335582717024622,
23
+ "eval_loss": 0.10384641587734222,
24
+ "eval_precision_macro": 0.9347320773183263,
25
+ "eval_precision_weighted": 0.9349217985380474,
26
+ "eval_recall_macro": 0.9338033327229445,
27
+ "eval_recall_weighted": 0.93359375,
28
+ "eval_runtime": 9.4737,
29
+ "eval_samples_per_second": 27.022,
30
+ "eval_steps_per_second": 6.756,
31
+ "step": 512
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "grad_norm": 5.7770538330078125,
36
+ "learning_rate": 1.7273933762797558e-05,
37
+ "loss": 0.0833,
38
+ "step": 1024
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "eval_accuracy": 0.9765625,
43
+ "eval_f1_macro": 0.9765567765567765,
44
+ "eval_f1_weighted": 0.9765596382783882,
45
+ "eval_loss": 0.05563850328326225,
46
+ "eval_precision_macro": 0.9767328244274809,
47
+ "eval_precision_weighted": 0.9766760496183207,
48
+ "eval_recall_macro": 0.9765000305194409,
49
+ "eval_recall_weighted": 0.9765625,
50
+ "eval_runtime": 9.4836,
51
+ "eval_samples_per_second": 26.994,
52
+ "eval_steps_per_second": 6.748,
53
+ "step": 1024
54
+ },
55
+ {
56
+ "epoch": 3.0,
57
+ "grad_norm": 0.13111276924610138,
58
+ "learning_rate": 1.4049861939731116e-05,
59
+ "loss": 0.0723,
60
+ "step": 1536
61
+ },
62
+ {
63
+ "epoch": 3.0,
64
+ "eval_accuracy": 0.96875,
65
+ "eval_f1_macro": 0.9687328244274809,
66
+ "eval_f1_weighted": 0.9687385496183205,
67
+ "eval_loss": 0.06124699488282204,
68
+ "eval_precision_macro": 0.9693135277217434,
69
+ "eval_precision_weighted": 0.9692008221773947,
70
+ "eval_recall_macro": 0.9686260147714094,
71
+ "eval_recall_weighted": 0.96875,
72
+ "eval_runtime": 9.4427,
73
+ "eval_samples_per_second": 27.111,
74
+ "eval_steps_per_second": 6.778,
75
+ "step": 1536
76
+ },
77
+ {
78
+ "epoch": 4.0,
79
+ "grad_norm": 0.0075853727757930756,
80
+ "learning_rate": 1.0194105002318014e-05,
81
+ "loss": 0.0413,
82
+ "step": 2048
83
+ },
84
+ {
85
+ "epoch": 4.0,
86
+ "eval_accuracy": 0.96875,
87
+ "eval_f1_macro": 0.9687423687423687,
88
+ "eval_f1_weighted": 0.9687461843711844,
89
+ "eval_loss": 0.08229334652423859,
90
+ "eval_precision_macro": 0.9689160305343512,
91
+ "eval_precision_weighted": 0.9688606870229008,
92
+ "eval_recall_macro": 0.9686870536531771,
93
+ "eval_recall_weighted": 0.96875,
94
+ "eval_runtime": 9.4556,
95
+ "eval_samples_per_second": 27.074,
96
+ "eval_steps_per_second": 6.768,
97
+ "step": 2048
98
+ }
99
+ ],
100
+ "logging_steps": 500,
101
+ "max_steps": 4096,
102
+ "num_input_tokens_seen": 0,
103
+ "num_train_epochs": 8,
104
+ "save_steps": 500,
105
+ "stateful_callbacks": {
106
+ "EarlyStoppingCallback": {
107
+ "args": {
108
+ "early_stopping_patience": 2,
109
+ "early_stopping_threshold": 0.0
110
+ },
111
+ "attributes": {
112
+ "early_stopping_patience_counter": 2
113
+ }
114
+ },
115
+ "TrainerControl": {
116
+ "args": {
117
+ "should_epoch_stop": false,
118
+ "should_evaluate": false,
119
+ "should_log": false,
120
+ "should_save": true,
121
+ "should_training_stop": true
122
+ },
123
+ "attributes": {}
124
+ }
125
+ },
126
+ "total_flos": 7626926277476352.0,
127
+ "train_batch_size": 4,
128
+ "trial_name": null,
129
+ "trial_params": null
130
+ }
checkpoint-2048/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05f014aae6457a5193b7b97676fb49f1f8e5a4d72875fe8b03696e481f3aa324
3
+ size 5240
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.49.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
logs/events.out.tfevents.1740652331.686e763fa1a3.6372.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b679ab2ba83443dd64c4ce1ad8fc68431d53c7b4e8729e949e77a6e9887185a
3
+ size 5048
logs/events.out.tfevents.1740652422.686e763fa1a3.6372.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f61ba655f9b9482c492b3b9d0281386398db0edc9c5bdd8042bffbc72875f99
3
+ size 8912
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a194e4caa903e2cc9a968fcee5892a44a70812c34b5fd6bcb2c94bd873271e26
3
+ size 2239618672
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 sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
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 sha256:05f014aae6457a5193b7b97676fb49f1f8e5a4d72875fe8b03696e481f3aa324
3
+ size 5240