Hugging Face's logo

uvegesistvan
/
wildmann_german_proposal_2a

TensorBoard
Safetensors
English
xlm-roberta
emotion-classification
text-analysis
Model card Files
xet
 Metrics Community
uvegesistvan commited on
Commit
7d21f5e
·
verified ·
1 Parent(s): c0a0fed

Upload folder using huggingface_hub

Browse files
Files changed (17) hide show
  1. checkpoint-10482/config.json +51 -0
  2. checkpoint-10482/model.safetensors +3 -0
  3. checkpoint-10482/optimizer.pt +3 -0
  4. checkpoint-10482/rng_state.pth +3 -0
  5. checkpoint-10482/scheduler.pt +3 -0
  6. checkpoint-10482/trainer_state.json +99 -0
  7. checkpoint-10482/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. model.safetensors +3 -0
  17. training_args.bin +3 -0
checkpoint-10482/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": "4.47.1",
48
+ "type_vocab_size": 1,
49
+ "use_cache": true,
50
+ "vocab_size": 250002
51
+ }
checkpoint-10482/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993874b814997520b7d3fd5c63b5b1ceda184ac865f8c9035a40e665676b69e4
3
+ size 2239647372
checkpoint-10482/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fb57458dc01f8e57667a72409ada81533a66dd9d28f821f720710084a803090
3
+ size 4479530129
checkpoint-10482/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7bc09298908479b7ed2a489f2f7b28713ec5f35cde55e6f61bf659f775eeb89
3
+ size 14244
checkpoint-10482/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d3696f11ea12030a2b34ecb9dafc09cabf998877302b8c702d03e73ad8e0aa8
3
+ size 1064
checkpoint-10482/trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.82375568151474,
3
+ "best_model_checkpoint": "model/checkpoint-10482",
4
+ "epoch": 3.0,
5
+ "eval_steps": 100,
6
+ "global_step": 10482,
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": 13.454610824584961,
14
+ "learning_rate": 8.333333333333334e-06,
15
+ "loss": 0.9656,
16
+ "step": 3494
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6960068699012452,
21
+ "eval_f1": 0.6915805800497401,
22
+ "eval_loss": 0.8458037376403809,
23
+ "eval_precision": 0.6950177453869647,
24
+ "eval_recall": 0.6960068699012452,
25
+ "eval_runtime": 73.3892,
26
+ "eval_samples_per_second": 95.205,
27
+ "eval_steps_per_second": 5.955,
28
+ "step": 3494
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 8.257609367370605,
33
+ "learning_rate": 6.666666666666667e-06,
34
+ "loss": 0.7655,
35
+ "step": 6988
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.6957206240160297,
40
+ "eval_f1": 0.7049808342361623,
41
+ "eval_loss": 0.8289042711257935,
42
+ "eval_precision": 0.7228825242379339,
43
+ "eval_recall": 0.6957206240160297,
44
+ "eval_runtime": 73.3472,
45
+ "eval_samples_per_second": 95.259,
46
+ "eval_steps_per_second": 5.958,
47
+ "step": 6988
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 14.953173637390137,
52
+ "learning_rate": 5e-06,
53
+ "loss": 0.6883,
54
+ "step": 10482
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.7028767711464148,
59
+ "eval_f1": 0.6995363087797226,
60
+ "eval_loss": 0.82375568151474,
61
+ "eval_precision": 0.6983847928305661,
62
+ "eval_recall": 0.7028767711464148,
63
+ "eval_runtime": 73.3522,
64
+ "eval_samples_per_second": 95.253,
65
+ "eval_steps_per_second": 5.958,
66
+ "step": 10482
67
+ }
68
+ ],
69
+ "logging_steps": 100,
70
+ "max_steps": 20964,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 6,
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": 7.813450749246106e+16,
96
+ "train_batch_size": 16,
97
+ "trial_name": null,
98
+ "trial_params": null
99
+ }
checkpoint-10482/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": "4.47.1",
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
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993874b814997520b7d3fd5c63b5b1ceda184ac865f8c9035a40e665676b69e4
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