Hugging Face's logo

ringorsolya
/
xlmRoBERTa_polish

TensorBoard
Safetensors
xlm-roberta
Model card Files Metrics Community
ringorsolya commited on
Commit
3a5a325
•
1 Parent(s): 0df45f1

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. .gitattributes +3 -0
  2. anger_benchmark.xlsx +0 -0
  3. checkpoint-2772/config.json +45 -0
  4. checkpoint-2772/model.safetensors +3 -0
  5. checkpoint-2772/optimizer.pt +3 -0
  6. checkpoint-2772/rng_state.pth +3 -0
  7. checkpoint-2772/scheduler.pt +3 -0
  8. checkpoint-2772/trainer_state.json +99 -0
  9. checkpoint-2772/training_args.bin +3 -0
  10. checkpoint-3696/config.json +45 -0
  11. checkpoint-3696/model.safetensors +3 -0
  12. checkpoint-3696/rng_state.pth +3 -0
  13. checkpoint-3696/scheduler.pt +3 -0
  14. checkpoint-3696/trainer_state.json +118 -0
  15. checkpoint-3696/training_args.bin +3 -0
  16. cleaned_anger_train.xlsx +0 -0
  17. config.json +29 -0
  18. events.out.tfevents.1729344456.e68f58a32709.1290.2 +3 -0
  19. events.out.tfevents.1729349929.e68f58a32709.33818.0 +3 -0
  20. events.out.tfevents.1729362050.e68f58a32709.84141.0 +3 -0
  21. events.out.tfevents.1730058868.7ef9627f8aa1.700.0 +3 -0
  22. guiltbert_train.xlsx +0 -0
  23. model.safetensors +3 -0
  24. mores_parl_speech_1998_2002_xlmRoberta_predictions.xlsx +3 -0
  25. mores_parl_speech_2010_2014_part_0_predictions.xlsx +3 -0
  26. pooled_v4_xlmRoberta_training.xlsx +3 -0
  27. test_data.xlsx +0 -0
  28. training_args.bin +3 -0
  29. xlm_roberta_polish_train_20241017.xlsx +0 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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
+ mores_parl_speech_1998_2002_xlmRoberta_predictions.xlsx filter=lfs diff=lfs merge=lfs -text
37
+ mores_parl_speech_2010_2014_part_0_predictions.xlsx filter=lfs diff=lfs merge=lfs -text
38
+ pooled_v4_xlmRoberta_training.xlsx filter=lfs diff=lfs merge=lfs -text
anger_benchmark.xlsx ADDED
Binary file (34.2 kB). View file
 
checkpoint-2772/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2,
27
+ "LABEL_3": 3,
28
+ "LABEL_4": 4,
29
+ "LABEL_5": 5
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "xlm-roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "output_past": true,
37
+ "pad_token_id": 1,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "multi_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.46.0",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 250002
45
+ }
checkpoint-2772/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be47d0ad2ecaa55bdce468bdaa68a8045e8a27f49f5ab0ab438cd20494c31bdf
3
+ size 1112217312
checkpoint-2772/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b07154ce1e8e6d8386ee5c552b6ebbb8da735e9c5eca291f9c36046e75a93ad6
3
+ size 2224554234
checkpoint-2772/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf89f4d131941ed2d32c937dbe883ce9eae411d5e1cb32633c6f6edb39e1bb1
3
+ size 14244
checkpoint-2772/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f42f4c95afb8d7bc18fd98fc37c6b8fc78802c71e4358ad882e021e631e7b19c
3
+ size 1064
checkpoint-2772/trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.05848415940999985,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/checkpoint-2772",
4
+ "epoch": 3.0,
5
+ "eval_steps": 100,
6
+ "global_step": 2772,
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": 5.851963043212891,
14
+ "learning_rate": 4.5e-06,
15
+ "loss": 0.261,
16
+ "step": 924
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.9312026002166848,
21
+ "eval_f1": 0.9304556698132427,
22
+ "eval_loss": 0.10791309922933578,
23
+ "eval_precision": 0.9337159575536489,
24
+ "eval_recall": 0.9312026002166848,
25
+ "eval_runtime": 49.9811,
26
+ "eval_samples_per_second": 36.934,
27
+ "eval_steps_per_second": 2.321,
28
+ "step": 924
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 0.24086147546768188,
33
+ "learning_rate": 4.000000000000001e-06,
34
+ "loss": 0.0812,
35
+ "step": 1848
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.9582881906825569,
40
+ "eval_f1": 0.9581837801589876,
41
+ "eval_loss": 0.06059493124485016,
42
+ "eval_precision": 0.9585273431262236,
43
+ "eval_recall": 0.9582881906825569,
44
+ "eval_runtime": 49.6996,
45
+ "eval_samples_per_second": 37.143,
46
+ "eval_steps_per_second": 2.334,
47
+ "step": 1848
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 0.1482285112142563,
52
+ "learning_rate": 3.5e-06,
53
+ "loss": 0.0501,
54
+ "step": 2772
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.9544962080173348,
59
+ "eval_f1": 0.9543281540493387,
60
+ "eval_loss": 0.05848415940999985,
61
+ "eval_precision": 0.9552102707240017,
62
+ "eval_recall": 0.9544962080173348,
63
+ "eval_runtime": 49.6249,
64
+ "eval_samples_per_second": 37.199,
65
+ "eval_steps_per_second": 2.338,
66
+ "step": 2772
67
+ }
68
+ ],
69
+ "logging_steps": 100,
70
+ "max_steps": 9240,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 10,
73
+ "save_steps": 100,
74
+ "stateful_callbacks": {
75
+ "EarlyStoppingCallback": {
76
+ "args": {
77
+ "early_stopping_patience": 2,
78
+ "early_stopping_threshold": 0.0
79
+ },
80
+ "attributes": {
81
+ "early_stopping_patience_counter": 0
82
+ }
83
+ },
84
+ "TrainerControl": {
85
+ "args": {
86
+ "should_epoch_stop": false,
87
+ "should_evaluate": false,
88
+ "should_log": false,
89
+ "should_save": true,
90
+ "should_training_stop": false
91
+ },
92
+ "attributes": {}
93
+ }
94
+ },
95
+ "total_flos": 1.165886956910592e+16,
96
+ "train_batch_size": 16,
97
+ "trial_name": null,
98
+ "trial_params": null
99
+ }
checkpoint-2772/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6c9b99ed9f50a85ea3cfb046c9b532d2109d14a126aa90a905841854114b554
3
+ size 5176
checkpoint-3696/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2,
27
+ "LABEL_3": 3,
28
+ "LABEL_4": 4,
29
+ "LABEL_5": 5
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "xlm-roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "output_past": true,
37
+ "pad_token_id": 1,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "multi_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.46.0",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 250002
45
+ }
checkpoint-3696/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51a09eddbb88499a94d3e8531491ab88e457b5d0ab74d8129b58c19891e2254e
3
+ size 1112217312
checkpoint-3696/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4750d2ef6f9083f7296a7fcbb7a25d3a29a00c11481cd6fe792a3688e02f841
3
+ size 14244
checkpoint-3696/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7be148d6578622b9a23ead50beea9d3af5dfc75be4998df2c499217cef45c00e
3
+ size 1064
checkpoint-3696/trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.04969688504934311,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/checkpoint-3696",
4
+ "epoch": 4.0,
5
+ "eval_steps": 100,
6
+ "global_step": 3696,
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": 5.851963043212891,
14
+ "learning_rate": 4.5e-06,
15
+ "loss": 0.261,
16
+ "step": 924
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.9312026002166848,
21
+ "eval_f1": 0.9304556698132427,
22
+ "eval_loss": 0.10791309922933578,
23
+ "eval_precision": 0.9337159575536489,
24
+ "eval_recall": 0.9312026002166848,
25
+ "eval_runtime": 49.9811,
26
+ "eval_samples_per_second": 36.934,
27
+ "eval_steps_per_second": 2.321,
28
+ "step": 924
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 0.24086147546768188,
33
+ "learning_rate": 4.000000000000001e-06,
34
+ "loss": 0.0812,
35
+ "step": 1848
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.9582881906825569,
40
+ "eval_f1": 0.9581837801589876,
41
+ "eval_loss": 0.06059493124485016,
42
+ "eval_precision": 0.9585273431262236,
43
+ "eval_recall": 0.9582881906825569,
44
+ "eval_runtime": 49.6996,
45
+ "eval_samples_per_second": 37.143,
46
+ "eval_steps_per_second": 2.334,
47
+ "step": 1848
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 0.1482285112142563,
52
+ "learning_rate": 3.5e-06,
53
+ "loss": 0.0501,
54
+ "step": 2772
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.9544962080173348,
59
+ "eval_f1": 0.9543281540493387,
60
+ "eval_loss": 0.05848415940999985,
61
+ "eval_precision": 0.9552102707240017,
62
+ "eval_recall": 0.9544962080173348,
63
+ "eval_runtime": 49.6249,
64
+ "eval_samples_per_second": 37.199,
65
+ "eval_steps_per_second": 2.338,
66
+ "step": 2772
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 0.11282943189144135,
71
+ "learning_rate": 3e-06,
72
+ "loss": 0.0371,
73
+ "step": 3696
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.9626218851570965,
78
+ "eval_f1": 0.9623565485461932,
79
+ "eval_loss": 0.04969688504934311,
80
+ "eval_precision": 0.9626465758175986,
81
+ "eval_recall": 0.9626218851570965,
82
+ "eval_runtime": 49.5559,
83
+ "eval_samples_per_second": 37.251,
84
+ "eval_steps_per_second": 2.341,
85
+ "step": 3696
86
+ }
87
+ ],
88
+ "logging_steps": 100,
89
+ "max_steps": 9240,
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": 1.554515942547456e+16,
115
+ "train_batch_size": 16,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }
checkpoint-3696/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6c9b99ed9f50a85ea3cfb046c9b532d2109d14a126aa90a905841854114b554
3
+ size 5176
cleaned_anger_train.xlsx ADDED
Binary file (817 kB). View file
 
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.1729344456.e68f58a32709.1290.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:625d00840be1e57493fa43f8a042729d8b949f3e93bceee9c52b440ce9010bf3
3
+ size 6367
events.out.tfevents.1729349929.e68f58a32709.33818.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bcff8fcefafcd2372ff6e9ef239b65b16f12ebc8d156ba74159141ad83105c4
3
+ size 8087
events.out.tfevents.1729362050.e68f58a32709.84141.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b6ac395189d44f9a141a07a8e6a37d812f6798bab7522f10eacc2282102da33
3
+ size 7404
events.out.tfevents.1730058868.7ef9627f8aa1.700.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ee7d420a28578202896069cc36931a02c66b54529cd29ce4ac1855bdf525e6
3
+ size 88
guiltbert_train.xlsx ADDED
Binary file (269 kB). View file
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e0fd8a7b04dc08c005a4cc83ddbeb6d29b7aca0275d6286eb32a6ceb01359f
3
+ size 1112205008
mores_parl_speech_1998_2002_xlmRoberta_predictions.xlsx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3ad0bf12c8238c2d90305338c6b0edba91ea1b23a959160ed6cced917da12b7
3
+ size 98915510
mores_parl_speech_2010_2014_part_0_predictions.xlsx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d382f2f650fe2346f76ae7fbbdd88d2d7fec58f7330d30db9fe20bda3c79819
3
+ size 74245658
pooled_v4_xlmRoberta_training.xlsx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c641f391ef8fa3c68a7509cc06d3d56cb2dd58d4955f0a46b89359628d78afa
3
+ size 8796228
test_data.xlsx ADDED
Binary file (128 kB). View file
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91465c5a6bad4d928dd773ccf8231c79bfb32b197332c29d7457d91c0bda618
3
+ size 5176
xlm_roberta_polish_train_20241017.xlsx ADDED
Binary file (886 kB). View file