Hugging Face's logo

uvegesistvan
/
wildmann_german_proposal_2b_GER_ENG_SLO

TensorBoard
Safetensors
Slovak
xlm-roberta
emotion-classification
text-analysis
machine-translation
Model card Files Metrics Community
uvegesistvan commited on
Commit
d7a4019
·
verified ·
1 Parent(s): 1be57bd

Upload folder using huggingface_hub

Browse files
Files changed (31) hide show
  1. checkpoint-23292/config.json +51 -0
  2. checkpoint-23292/model.safetensors +3 -0
  3. checkpoint-23292/optimizer.pt +3 -0
  4. checkpoint-23292/rng_state.pth +3 -0
  5. checkpoint-23292/scheduler.pt +3 -0
  6. checkpoint-23292/trainer_state.json +156 -0
  7. checkpoint-23292/training_args.bin +3 -0
  8. config.json +51 -0
  9. events.out.tfevents.1734268801.5dc78d0c0094.597.10 +3 -0
  10. events.out.tfevents.1734292683.26dae68edbc1.519.0 +3 -0
  11. events.out.tfevents.1734293482.15565a6fdb0d.517.0 +3 -0
  12. events.out.tfevents.1734299316.15565a6fdb0d.14799.0 +3 -0
  13. events.out.tfevents.1734305996.15565a6fdb0d.14799.1 +3 -0
  14. events.out.tfevents.1736275701.ccf8e4cfc100.602.0 +3 -0
  15. events.out.tfevents.1736278450.ccf8e4cfc100.602.1 +3 -0
  16. events.out.tfevents.1736347759.affcea672b22.1013.0 +3 -0
  17. events.out.tfevents.1736347909.a7ec1308ad87.517.0 +3 -0
  18. events.out.tfevents.1736348086.a7ec1308ad87.1015.0 +3 -0
  19. events.out.tfevents.1736348328.892f0a65915d.511.0 +3 -0
  20. events.out.tfevents.1736529172.1a9a4426b2c0.783.0 +3 -0
  21. events.out.tfevents.1736529480.a0c18d20ace0.511.0 +3 -0
  22. events.out.tfevents.1736549406.f0c728e9d75e.800.0 +3 -0
  23. events.out.tfevents.1736591693.018665a8db46.767.0 +3 -0
  24. events.out.tfevents.1736779680.992121edcd4f.758.0 +3 -0
  25. events.out.tfevents.1736786968.edbe65884e1a.520.0 +3 -0
  26. events.out.tfevents.1736800088.b710a0a3181d.525.0 +3 -0
  27. events.out.tfevents.1736800252.76efb2166462.509.0 +3 -0
  28. events.out.tfevents.1736810702.76efb2166462.509.1 +3 -0
  29. events.out.tfevents.1736877978.fdfe31be4ffa.519.0 +3 -0
  30. model.safetensors +3 -0
  31. training_args.bin +3 -0
checkpoint-23292/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 4096,
26
+ "label2id": {
27
+ "LABEL_0": 0,
28
+ "LABEL_1": 1,
29
+ "LABEL_2": 2,
30
+ "LABEL_3": 3,
31
+ "LABEL_4": 4,
32
+ "LABEL_5": 5,
33
+ "LABEL_6": 6,
34
+ "LABEL_7": 7,
35
+ "LABEL_8": 8
36
+ },
37
+ "layer_norm_eps": 1e-05,
38
+ "max_position_embeddings": 514,
39
+ "model_type": "xlm-roberta",
40
+ "num_attention_heads": 16,
41
+ "num_hidden_layers": 24,
42
+ "output_past": true,
43
+ "pad_token_id": 1,
44
+ "position_embedding_type": "absolute",
45
+ "problem_type": "single_label_classification",
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.48.0",
48
+ "type_vocab_size": 1,
49
+ "use_cache": true,
50
+ "vocab_size": 250002
51
+ }
checkpoint-23292/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae9578f587bdb45a9d7115671b4a59267ce1417a34f955e86e387cdff7850361
3
+ size 2239647372
checkpoint-23292/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e0a8a93e2c16ff37977602b602b2e3e625d0005a822a33cb8d6c65a2f995b48
3
+ size 4479530129
checkpoint-23292/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6b337534045ef5f502970dd227169d0360e5f85040a4d8e477a251c01e482b
3
+ size 14244
checkpoint-23292/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:621282ade586ed8b2e7e2837d1f5c8e6efe06b96076884669666d34db683780f
3
+ size 1064
checkpoint-23292/trainer_state.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.1302926540374756,
3
+ "best_model_checkpoint": "model/checkpoint-23292",
4
+ "epoch": 6.0,
5
+ "eval_steps": 100,
6
+ "global_step": 23292,
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": 9.472450256347656,
14
+ "learning_rate": 8.333333333333334e-06,
15
+ "loss": 2.1616,
16
+ "step": 3882
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.28013910355486865,
21
+ "eval_f1": 0.14709299072288587,
22
+ "eval_loss": 1.989043951034546,
23
+ "eval_precision": 0.10252086351966208,
24
+ "eval_recall": 0.28013910355486865,
25
+ "eval_runtime": 99.7141,
26
+ "eval_samples_per_second": 77.863,
27
+ "eval_steps_per_second": 4.874,
28
+ "step": 3882
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 18.01424217224121,
33
+ "learning_rate": 6.666666666666667e-06,
34
+ "loss": 1.6549,
35
+ "step": 7764
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.5072127769191138,
40
+ "eval_f1": 0.4525682474288517,
41
+ "eval_loss": 1.4202383756637573,
42
+ "eval_precision": 0.4940970315174013,
43
+ "eval_recall": 0.5072127769191138,
44
+ "eval_runtime": 99.7908,
45
+ "eval_samples_per_second": 77.803,
46
+ "eval_steps_per_second": 4.87,
47
+ "step": 7764
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 9.260454177856445,
52
+ "learning_rate": 5e-06,
53
+ "loss": 1.3957,
54
+ "step": 11646
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.5495878413189078,
59
+ "eval_f1": 0.5150604344923556,
60
+ "eval_loss": 1.381932020187378,
61
+ "eval_precision": 0.5532737809304744,
62
+ "eval_recall": 0.5495878413189078,
63
+ "eval_runtime": 99.7636,
64
+ "eval_samples_per_second": 77.824,
65
+ "eval_steps_per_second": 4.872,
66
+ "step": 11646
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 5.384854316711426,
71
+ "learning_rate": 3.3333333333333333e-06,
72
+ "loss": 1.3006,
73
+ "step": 15528
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.5677485832045337,
78
+ "eval_f1": 0.5276816726729678,
79
+ "eval_loss": 1.2678101062774658,
80
+ "eval_precision": 0.5656278860844167,
81
+ "eval_recall": 0.5677485832045337,
82
+ "eval_runtime": 99.8317,
83
+ "eval_samples_per_second": 77.771,
84
+ "eval_steps_per_second": 4.868,
85
+ "step": 15528
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 21.27960205078125,
90
+ "learning_rate": 1.6666666666666667e-06,
91
+ "loss": 1.2084,
92
+ "step": 19410
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.5971148892323545,
97
+ "eval_f1": 0.599084527031254,
98
+ "eval_loss": 1.1466307640075684,
99
+ "eval_precision": 0.6357226057346971,
100
+ "eval_recall": 0.5971148892323545,
101
+ "eval_runtime": 100.1224,
102
+ "eval_samples_per_second": 77.545,
103
+ "eval_steps_per_second": 4.854,
104
+ "step": 19410
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 79.17021179199219,
109
+ "learning_rate": 0.0,
110
+ "loss": 1.1125,
111
+ "step": 23292
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.6040700669757857,
116
+ "eval_f1": 0.6166581532888394,
117
+ "eval_loss": 1.1302926540374756,
118
+ "eval_precision": 0.6409292895247615,
119
+ "eval_recall": 0.6040700669757857,
120
+ "eval_runtime": 99.9007,
121
+ "eval_samples_per_second": 77.717,
122
+ "eval_steps_per_second": 4.865,
123
+ "step": 23292
124
+ }
125
+ ],
126
+ "logging_steps": 100,
127
+ "max_steps": 23292,
128
+ "num_input_tokens_seen": 0,
129
+ "num_train_epochs": 6,
130
+ "save_steps": 100,
131
+ "stateful_callbacks": {
132
+ "EarlyStoppingCallback": {
133
+ "args": {
134
+ "early_stopping_patience": 2,
135
+ "early_stopping_threshold": 0.0
136
+ },
137
+ "attributes": {
138
+ "early_stopping_patience_counter": 0
139
+ }
140
+ },
141
+ "TrainerControl": {
142
+ "args": {
143
+ "should_epoch_stop": false,
144
+ "should_evaluate": false,
145
+ "should_log": false,
146
+ "should_save": true,
147
+ "should_training_stop": true
148
+ },
149
+ "attributes": {}
150
+ }
151
+ },
152
+ "total_flos": 1.7363130691873075e+17,
153
+ "train_batch_size": 16,
154
+ "trial_name": null,
155
+ "trial_params": null
156
+ }
checkpoint-23292/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de273838f57747afd3006ebd4c66d232f4334f36315cdb16f0ef458d93b5f23
3
+ size 5240
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 4096,
26
+ "label2id": {
27
+ "LABEL_0": 0,
28
+ "LABEL_1": 1,
29
+ "LABEL_2": 2,
30
+ "LABEL_3": 3,
31
+ "LABEL_4": 4,
32
+ "LABEL_5": 5,
33
+ "LABEL_6": 6,
34
+ "LABEL_7": 7,
35
+ "LABEL_8": 8
36
+ },
37
+ "layer_norm_eps": 1e-05,
38
+ "max_position_embeddings": 514,
39
+ "model_type": "xlm-roberta",
40
+ "num_attention_heads": 16,
41
+ "num_hidden_layers": 24,
42
+ "output_past": true,
43
+ "pad_token_id": 1,
44
+ "position_embedding_type": "absolute",
45
+ "problem_type": "single_label_classification",
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.48.0",
48
+ "type_vocab_size": 1,
49
+ "use_cache": true,
50
+ "vocab_size": 250002
51
+ }
events.out.tfevents.1734268801.5dc78d0c0094.597.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc1315c7e1f2183cb5b32925df2e7b72f36542226b646d07a45f3c2ae0533f0
3
+ size 8513
events.out.tfevents.1734292683.26dae68edbc1.519.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:153851a01c1db2c0602694cc5524d930f1f95c7a7c3a8cd4d23bbb7b09b9dc0a
3
+ size 5395
events.out.tfevents.1734293482.15565a6fdb0d.517.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5315719c053e1861da202c80e15d78116f848d40ccf4a2f40dcb34688c8375dc
3
+ size 7444
events.out.tfevents.1734299316.15565a6fdb0d.14799.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30436099c0ccf2daef57aa51b47cca5db54f956c27940eddb55b1a3664918dc
3
+ size 8481
events.out.tfevents.1734305996.15565a6fdb0d.14799.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60026a51a67f1cd87355d4a35d74e7f092d77e110549e5808328478f692f45f4
3
+ size 9164
events.out.tfevents.1736275701.ccf8e4cfc100.602.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6f36308fbef6bcf0fd81c4e7d64d450c8eaf5800a624df96fa1aa07a6895801
3
+ size 5395
events.out.tfevents.1736278450.ccf8e4cfc100.602.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f65837e8097fba7e1c62f4323abc004c45d8d76c915594caedfac13d1992850
3
+ size 9183
events.out.tfevents.1736347759.affcea672b22.1013.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eddd5f5bb8672975a8cd0b0171c1ba334ad85b542ee025aa522b9df4570fa05
3
+ size 5395
events.out.tfevents.1736347909.a7ec1308ad87.517.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49bcc672afaf6045e973673ac75f3625ea2ad3cacf8d098f50e4385bad595f79
3
+ size 5395
events.out.tfevents.1736348086.a7ec1308ad87.1015.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bf5216291240dba6beaa7e66bdb7888f5b358c46ed8ddd08f935a4e380772ec
3
+ size 5395
events.out.tfevents.1736348328.892f0a65915d.511.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:222f7266238deb428ba3800c68968ba8f80f58aa05b3318929ffb0a9a7e5b1e9
3
+ size 8481
events.out.tfevents.1736529172.1a9a4426b2c0.783.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33eb538b3bfb14a8557b8f6934c99a2e7e2dd0f44dc3356c508585c116b54c6a
3
+ size 5395
events.out.tfevents.1736529480.a0c18d20ace0.511.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30b325f8dcf516b2f62ef7c4afcd44f3ee3e91cf458292cf54c978f60e03335e
3
+ size 8481
events.out.tfevents.1736549406.f0c728e9d75e.800.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ad8887dbed3fc02d3433ce314d61e48216fcfe486bfb03b775b46e8b096da25
3
+ size 9879
events.out.tfevents.1736591693.018665a8db46.767.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def3970897f3c61f36c37d5fdd7c1548f71ce41fd8bf64d66d123c8434a912d7
3
+ size 8481
events.out.tfevents.1736779680.992121edcd4f.758.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8712ded618b7b5d8d4c5a1c6e4592a41803be18f4972c3dbd3448f1476f45581
3
+ size 5395
events.out.tfevents.1736786968.edbe65884e1a.520.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d4a4ead113d21b39a54eeccfd53524f766aa295284112fbd9883ee16a3590a
3
+ size 8481
events.out.tfevents.1736800088.b710a0a3181d.525.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7960d3f271516197b4fca8ecc200129e232a2b4d6742e9d67319e851a14b7bd5
3
+ size 5395
events.out.tfevents.1736800252.76efb2166462.509.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaaf95c473e47d2858e8b952a60af2ef6e488137e173661044d55573ba6ab7e7
3
+ size 8481
events.out.tfevents.1736810702.76efb2166462.509.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f04aa245562aab8ec019246ab8df2711f1b2418025c6a815e4cc1b009b1edb64
3
+ size 9183
events.out.tfevents.1736877978.fdfe31be4ffa.519.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de2700accd244a73c23d308acd358c827098a6eaf88260161a299a4b77ade41f
3
+ size 9879
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae9578f587bdb45a9d7115671b4a59267ce1417a34f955e86e387cdff7850361
3
+ size 2239647372
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de273838f57747afd3006ebd4c66d232f4334f36315cdb16f0ef458d93b5f23
3
+ size 5240